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

    Neuronpedia

    INDEX
    Explanations

    Script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standings
    -0.08
     होगी
    -0.08
     countryside
    -0.07
     citt
    -0.07
     приг
    -0.07
    ific
    -0.07
     conqu
    -0.07
     पूर्व
    -0.07
     arenas
    -0.07
     الطرق
    -0.07
    POSITIVE LOGITS
    Inside
    0.11
     inside
    0.10
    _inside
    0.10
     внутри
    0.09
     beads
    0.09
     ভিত
    0.09
    inside
    0.08
     Inside
    0.08
    直属
    0.08
    Dentro
    0.08
    Act Density 0.002%

    No Known Activations