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

    Neuronpedia

    INDEX
    Explanations

    on the phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pedestal
    0.77
     pedest
    0.71
    لك
    0.62
    ットフォーム
    0.62
     piatta
    0.62
    bases
    0.62
     terrain
    0.62
    pe
    0.61
    ք
    0.61
    miyor
    0.61
    POSITIVE LOGITS
     move
    1.07
     rise
    0.97
     downside
    0.89
     fly
    0.88
    move
    0.84
     loose
    0.81
     decline
    0.80
     spot
    0.79
     flip
    0.77
     contrary
    0.76
    Act Density 0.138%

    No Known Activations