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

    Neuronpedia

    INDEX
    Explanations

    information about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     her
    1.94
     his
    1.90
     various
    1.89
     into
    1.83
     in
    1.81
     on
    1.78
     of
    1.78
     its
    1.77
     the
    1.69
    她在
    1.67
    POSITIVE LOGITS
    Resp
    1.55
     animale
    1.45
     consentimiento
    1.42
     Nuss
    1.42
     chiedere
    1.36
     respuestas
    1.33
    astudio
    1.33
     lawns
    1.32
    煅
    1.31
     Resp
    1.28
    Act Density 1.108%

    No Known Activations