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

    Neuronpedia

    INDEX
    Explanations

    streaming rendering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    矵
    0.44
    嘮
    0.42
    ठबंधन
    0.41
    ᓛ
    0.41
     komma
    0.38
     aggravate
    0.38
     Counc
    0.38
    ház
    0.38
     allah
    0.37
    屬於
    0.37
    POSITIVE LOGITS
     방정식
    0.38
    Marvel
    0.37
    leukin
    0.37
     всему
    0.36
     offspring
    0.36
    ívar
    0.36
     tricked
    0.36
    secret
    0.36
    isha
    0.35
    (`/
    0.35
    Act Density 0.000%

    No Known Activations