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

    Neuronpedia

    INDEX
    Explanations

    Cartesian coordinates, audience, lives, hooked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enca
    0.44
     miatt
    0.42
    沉
    0.42
     Y
    0.42
     mennes
    0.42
     T
    0.41
     Guinea
    0.41
     EVA
    0.41
    既
    0.40
     Yhat
    0.40
    POSITIVE LOGITS
    ۴
    0.46
    street
    0.44
    –
    0.44
    }",
    0.43
     அடைய
    0.43
    ździe
    0.42
    }"]
    0.42
    प्रीत
    0.41
    "},
    0.41
    ༡
    0.41
    Act Density 0.006%

    No Known Activations