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

    Neuronpedia

    INDEX
    Explanations

    programming import statements in code

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

    import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ]();
    -0.60
     viewType
    -0.55
     interior
    -0.52
    ViewHolder
    -0.52
     Wallflower
    -0.50
    abetes
    -0.47
     contest
    -0.47
     internal
    -0.46
    URE
    -0.46
    sen
    -0.46
    POSITIVE LOGITS
    Autoritní
    0.70
     chrétiens
    0.66
     réfrig
    0.63
     indisponible
    0.61
    Personendaten
    0.58
     kasarigan
    0.58
     cristiana
    0.56
     Exactos
    0.56
    åk
    0.54
    Inflater
    0.54
    Act Density 0.005%

    No Known Activations