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

    Neuronpedia

    INDEX
    Explanations

    news stories

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dictionaries
    -0.07
     Pants
    -0.07
     Validation
    -0.06
     Demonstr
    -0.06
     Tao
    -0.06
     Jacket
    -0.06
    porno
    -0.06
    Explicit
    -0.06
     Astros
    -0.06
    -description
    -0.06
    POSITIVE LOGITS
     pretending
    0.08
     ic
    0.06
    mm
    0.06
    ampa
    0.06
    nesota
    0.06
    (),"
    0.06
     aria
    0.06
    _generated
    0.06
    (comm
    0.06
     Construct
    0.06
    Act Density 0.000%

    No Known Activations