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

    Neuronpedia

    INDEX
    Explanations

    text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    üml
    -0.06
     thấy
    -0.06
    DITION
    -0.06
    usalem
    -0.06
     maur
    -0.06
    IRA
    -0.06
    νοια
    -0.06
     rall
    -0.06
    xad
    -0.06
    yw
    -0.06
    POSITIVE LOGITS
     either
    0.07
     colle
    0.06
     Caught
    0.06
    �
    0.06
    패
    0.06
     Ε
    0.06
     Een
    0.06
    不要
    0.06
    enen
    0.06
    (',');↵
    0.06
    Act Density 0.000%

    No Known Activations