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

    Neuronpedia

    INDEX
    Explanations

    Theodore

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >';
    -0.07
     Госп
    -0.07
    mensaje
    -0.06
    なんて
    -0.06
    $/,
    -0.05
     ber
    -0.05
    -0.05
    -0.05
    Wenn
    -0.05
    -0.05
    POSITIVE LOGITS
     Electro
    0.07
    dek
    0.07
     Races
    0.07
    odox
    0.06
    (USER
    0.06
    emouth
    0.06
     getTitle
    0.06
     повинна
    0.06
     TELE
    0.06
     Kills
    0.06
    Act Density 0.002%

    No Known Activations