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

    Neuronpedia

    INDEX
    Explanations

    such a thing as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.40
    -
    0.39
    enarios
    0.37
     that
    0.36
    <0x0D>
    0.36
    olone
    0.36
     whose
    0.35
    0.35
     with
    0.35
     who
    0.35
    POSITIVE LOGITS
     aplicação
    0.48
    ในการ
    0.48
     îmb
    0.48
     mantener
    0.46
     управление
    0.45
     gestión
    0.45
     administrar
    0.44
     hyvä
    0.43
     kasutada
    0.43
     управлять
    0.43
    Act Density 0.007%

    No Known Activations