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

    Neuronpedia

    INDEX
    Explanations

    welcome

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Parts
    -0.07
     तहत
    -0.07
    raison
    -0.07
     Hoffman
    -0.07
     JNICALL
    -0.07
     prim
    -0.06
     Forget
    -0.06
    nez
    -0.06
     تت
    -0.06
    aic
    -0.06
    POSITIVE LOGITS
     welcome
    0.11
     dissoci
    0.06
     manifest
    0.06
     Recreation
    0.06
     battle
    0.06
     appreciated
    0.06
    Launching
    0.06
    community
    0.06
     perceptions
    0.06
     elders
    0.06
    Act Density 0.003%

    No Known Activations