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

    Neuronpedia

    INDEX
    Explanations

    helpline numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clumps
    0.69
     discs
    0.64
     prevent
    0.62
     考え
    0.62
     dese
    0.61
     depend
    0.60
    दृ
    0.60
     hear
    0.59
     disk
    0.59
     diagnostics
    0.59
    POSITIVE LOGITS
     Toll
    0.97
     +(
    0.96
    電話
    0.95
     toll
    0.93
    电话
    0.90
    Phone
    0.87
    Tel
    0.87
     hotline
    0.86
     teléfono
    0.83
    Call
    0.83
    Act Density 0.576%

    No Known Activations