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

    Neuronpedia

    INDEX
    Explanations

    patterns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nakalista
    -0.98
    IntoConstraints
    -0.75
     repay
    -0.74
     Mud
    -0.71
    Mud
    -0.69
     Courtesy
    -0.68
    MLLoader
    -0.68
     שוליים
    -0.67
     repaid
    -0.66
     mud
    -0.65
    POSITIVE LOGITS
    day
    0.55
    the
    0.54
    scal
    0.50
    sspiel
    0.50
    oredCriteria
    0.49
    Sec
    0.48
     effective
    0.47
    lla
    0.47
     period
    0.47
    dun
    0.47
    Act Density 0.807%

    No Known Activations