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

    Neuronpedia

    INDEX
    Explanations

    all human life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Helping
    0.80
    Helping
    0.78
     aidant
    0.78
     postgraduate
    0.73
     assistance
    0.73
    Pres
    0.71
     Gong
    0.69
    éu
    0.69
     midwifery
    0.69
     असर
    0.68
    POSITIVE LOGITS
     ABOUT
    0.79
    defini
    0.75
    about
    0.74
    鱔
    0.73
    soul
    0.71
     US
    0.71
     About
    0.69
     ECONOM
    0.68
     deline
    0.67
     USAF
    0.67
    Act Density 0.000%

    No Known Activations