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

    Neuronpedia

    INDEX
    Explanations

    Danganronpa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bcrypt
    -0.08
     cannabino
    -0.08
     Cann
    -0.08
     expiry
    -0.08
     Nürnberg
    -0.08
    ONDON
    -0.08
     gordura
    -0.08
     paddle
    -0.08
     cariño
    -0.08
     devuelve
    -0.08
    POSITIVE LOGITS
    truth
    0.09
     truthful
    0.09
    Truth
    0.09
     convinced
    0.08
     cheating
    0.08
    _truth
    0.08
    _statement
    0.08
     bursting
    0.08
     Analyst
    0.08
    真
    0.08
    Act Density 0.001%

    No Known Activations