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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ôm
    -0.08
    Disney
    -0.07
     נוספת
    -0.07
     Definitely
    -0.07
     Hôm
    -0.07
     proves
    -0.07
    ém
    -0.07
    漤
    -0.07
     בשנת
    -0.07
    闪过
    -0.07
    POSITIVE LOGITS
    מנהיג
    0.07
     implemented
    0.07
     zenith
    0.07
    용
    0.07
    PHA
    0.07
    вет
    0.07
     iP
    0.07
    0.07
    _qp
    0.07
    udents
    0.07
    Act Density 0.005%

    No Known Activations