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

    Neuronpedia

    INDEX
    Explanations

    elements of categorization and classification in a text

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

    first, different, each

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.56
     "..\..\..\
    -0.53
    onOptions
    -0.48
     Walkover
    -0.47
    djangoproject
    -0.47
    tagHelperRunner
    -0.47
     Infórmanos
    -0.47
    Autoritní
    -0.46
    /**
    -0.46
    ########.
    -0.45
    POSITIVE LOGITS
    分别是
    0.55
     First
    0.51
    分别
    0.49
     Novice
    0.47
    それぞれ
    0.47
     ranging
    0.47
     different
    0.46
     Beginner
    0.46
     Each
    0.46
     primero
    0.46
    Act Density 0.160%

    No Known Activations