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

    Neuronpedia

    INDEX
    Explanations

    references to data types and structures in programming contexts

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

    bits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.54
    <bos>
    -0.44
    ungsver
    -0.42
     pelúcia
    -0.41
    jfree
    -0.36
    FindBy
    -0.36
    ]})
    -0.35
     resourceCulture
    -0.35
    displaystyle
    -0.34
     Chwiliwch
    -0.34
    POSITIVE LOGITS
    Bits
    2.42
     Bits
    2.33
    bits
    2.30
     bits
    2.27
    BITS
    1.80
     BITS
    1.71
     pieces
    1.03
     Pieces
    0.98
    pieces
    0.96
     parts
    0.91
    Act Density 0.005%

    No Known Activations