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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bold
    -0.07
    IGH
    -0.07
     entrepreneurial
    -0.07
     needy
    -0.07
    laden
    -0.07
    iful
    -0.07
     kost
    -0.06
    eken
    -0.06
    .sha
    -0.06
     brace
    -0.06
    POSITIVE LOGITS
    (">
    0.07
    ami
    0.06
     ث
    0.06
    Module
    0.06
    学会
    0.06
    とき
    0.06
    Salvar
    0.06
    曾
    0.06
     pueden
    0.06
     Θεσσα
    0.06
    Act Density 0.000%

    No Known Activations