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

    Neuronpedia

    INDEX
    Explanations

    If/can do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     optimized
    0.47
     doll
    0.46
     uncut
    0.46
     lego
    0.45
     cra
    0.44
    0.44
     afro
    0.44
     porto
    0.44
     stronger
    0.43
     occasional
    0.43
    POSITIVE LOGITS
    Khokhlov
    0.54
    ریشن
    0.50
    ﺓ
    0.47
    partnership
    0.47
    кович
    0.47
    Rural
    0.46
    इक
    0.44
    Hearing
    0.44
    تھی
    0.44
    ків
    0.43
    Act Density 0.007%

    No Known Activations