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

    Neuronpedia

    INDEX
    Explanations

    Jesus, mirror, mind, innocent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    자
    0.60
     sito
    0.59
     granular
    0.58
     Dell
    0.55
    arik
    0.52
    બસ
    0.52
     caractéristique
    0.50
     понима
    0.49
    바
    0.49
    ᓇ
    0.48
    POSITIVE LOGITS
    }-
    0.66
    dirs
    0.51
    ITTING
    0.50
    pref
    0.50
    }{$
    0.49
    }+
    0.49
    uffle
    0.49
     NLP
    0.49
    }%
    0.48
    jy
    0.48
    Act Density 0.000%

    No Known Activations