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

    Neuronpedia

    INDEX
    Explanations

    svg code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curse
    -0.07
    ☢
    -0.07
    منح
    -0.07
    :hover
    -0.07
     Sapphire
    -0.06
    seite
    -0.06
    _quant
    -0.06
    icious
    -0.06
    蔻
    -0.06
    _verification
    -0.06
    POSITIVE LOGITS
    (",",
    0.07
     dan
    0.07
    BIN
    0.07
     particularly
    0.07
    allon
    0.07
    仍然
    0.07
     churn
    0.07
    aired
    0.07
     Ill
    0.07
    .sin
    0.07
    Act Density 0.002%

    No Known Activations