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

    Neuronpedia

    INDEX
    Explanations

    error handling and code execution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eny
    0.41
    stuk
    0.40
     grinned
    0.40
    ｃｍ
    0.39
     transplantation
    0.38
     clad
    0.37
    relu
    0.37
     പൊതു
    0.37
    uiar
    0.37
    sière
    0.37
    POSITIVE LOGITS
    disabled
    0.44
    orderby
    0.42
    쥐
    0.40
    get
    0.40
    cross
    0.38
    onSubmit
    0.38
    paginate
    0.38
    older
    0.37
     paginate
    0.37
    waffe
    0.37
    Act Density 0.142%

    No Known Activations