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

    Neuronpedia

    INDEX
    Explanations

    toxicity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucha
    -0.07
    olute
    -0.06
     Bottle
    -0.06
    š
    -0.06
    ani
    -0.06
     gb
    -0.06
     wave
    -0.06
    üns
    -0.06
    ahl
    -0.06
     Rick
    -0.06
    POSITIVE LOGITS
    注册
    0.07
    velope
    0.07
    (bean
    0.06
     Japon
    0.06
    รด
    0.06
    +k
    0.06
     besie
    0.06
    :t
    0.06
    packageName
    0.06
     kazan
    0.06
    Act Density 0.041%

    No Known Activations