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

    Neuronpedia

    INDEX
    Explanations

    organizations and health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ander
    0.32
    㓶
    0.29
     ou
    0.29
     şu
    0.28
     ikki
    0.28
     sive
    0.27
     ആൻ
    0.27
     भए
    0.27
    unehmen
    0.27
     Năm
    0.27
    POSITIVE LOGITS
    ulina
    0.30
     വിവിധ
    0.30
    AME
    0.30
    Optimal
    0.29
    Via
    0.29
    Attribute
    0.29
    Ciao
    0.29
    🇮
    0.29
    FACE
    0.28
    abhavena
    0.28
    Act Density 0.019%

    No Known Activations