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

    Neuronpedia

    INDEX
    Explanations

    recruiting and recruiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ка
    1.23
    ки
    1.14
    ك
    0.93
    ку
    0.90
    ب
    0.88
    h
    0.84
    я
    0.84
    ia
    0.81
    ра
    0.80
    ή
    0.79
    POSITIVE LOGITS
     recruited
    0.94
     recruiting
    0.93
     recruiters
    0.86
     Recruit
    0.85
    л
    0.85
     invitations
    0.81
    ،
    0.81
     recruitment
    0.80
    ない
    0.78
     recruit
    0.78
    Act Density 0.002%

    No Known Activations