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

    Neuronpedia

    INDEX
    Explanations

    chicken breast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    0.90
    Q
    0.81
    T
    0.80
    Que
    0.79
    E
    0.78
    W
    0.78
    H
    0.75
    The
    0.74
    Number
    0.74
    AN
    0.72
    POSITIVE LOGITS
    f
    0.65
     repealed
    0.65
     weekdays
    0.64
     shoots
    0.63
    t
    0.63
     which
    0.62
    و
    0.62
     wasteland
    0.61
     matchups
    0.61
     overruled
    0.59
    Act Density 0.001%

    No Known Activations