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

    Neuronpedia

    INDEX
    Explanations

    urls (e.g. https://web)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    My
    0.77
    q
    0.70
    add
    0.68
    app
    0.67
    5
    0.67
    7
    0.65
    0
    0.64
    6
    0.64
    8
    0.64
    1
    0.64
    POSITIVE LOGITS
     terroir
    0.62
     люд
    0.61
     Ork
    0.60
     Société
    0.59
    "{@
    0.56
     glPopMatrix
    0.55
     관
    0.55
     Policing
    0.54
     currentState
    0.54
     terdapat
    0.54
    Act Density 0.064%

    No Known Activations