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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Čes
    -0.07
    Spot
    -0.07
     Fucking
    -0.06
    데이트
    -0.06
    atrigesimal
    -0.06
    надлеж
    -0.06
     Girlfriend
    -0.06
    访问
    -0.06
    Stock
    -0.06
    _Post
    -0.06
    POSITIVE LOGITS
    )];
    0.06
     anterior
    0.06
     unregister
    0.06
    .Broadcast
    0.06
     Skype
    0.06
    clarations
    0.06
     prior
    0.06
     Oktober
    0.06
     cheering
    0.06
     jur
    0.06
    Act Density 0.003%

    No Known Activations