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

    Neuronpedia

    INDEX
    Explanations

    sales advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Planning
    -0.07
    句话
    -0.06
     Crossing
    -0.06
    athers
    -0.06
     ду
    -0.06
    sap
    -0.06
     lul
    -0.06
     century
    -0.06
    バー
    -0.06
     Container
    -0.06
    POSITIVE LOGITS
    čku
    0.07
    .yahoo
    0.07
     соот
    0.06
    िश
    0.06
    erald
    0.06
    าหล
    0.06
     Claudia
    0.06
    egment
    0.06
     sme
    0.06
    říklad
    0.06
    Act Density 0.008%

    No Known Activations