Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    decimal points or punctuation in numerical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with numpy arrays using `.stack`, `.unique`, or `.array`

    np_acts-logits-general · gemini-2.0-flash

    numpy array operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __':
    -0.81
    ContentAlignment
    -0.78
     betweenstory
    -0.77
    __":
    -0.71
    hasMoreElements
    -0.71
    apimachinery
    -0.71
     itſelf
    -0.68
    Földrajzportál
    -0.68
    MergeFrom
    -0.68
    cinogenicity
    -0.66
    POSITIVE LOGITS
     MonoBehaviour
    0.65
     (_.
    0.65
    miento
    0.60
    )$_
    0.59
     (!__
    0.56
     *
    0.56
     ευ
    0.56
    xia
    0.55
     Pha
    0.53
    ).__
    0.53
    Act Density 0.062%

    No Known Activations