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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     museums
    -0.07
    Dick
    -0.07
     Billing
    -0.06
    _ABORT
    -0.06
    .period
    -0.06
     Violence
    -0.06
     protection
    -0.06
    =-
    -0.06
    Items
    -0.06
    fastcall
    -0.06
    POSITIVE LOGITS
     following
    0.08
    following
    0.07
    %).↵↵
    0.07
     responding
    0.06
    ิงห
    0.06
    源
    0.06
     catchy
    0.06
    _ini
    0.06
    Д
    0.06
    стит
    0.06
    Act Density 0.027%

    No Known Activations