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

    Neuronpedia

    INDEX
    Explanations

    solely for purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ों
    1.00
    ྥ
    0.99
    く
    0.99
     którzy
    0.95
    джу
    0.95
    ал
    0.94
     périph
    0.94
    𝚍
    0.93
    ات
    0.91
    オブ
    0.91
    POSITIVE LOGITS
     for
    1.16
     and
    1.14
     only
    1.13
     at
    1.13
     therefore
    1.07
     to
    1.06
    ];
    1.02
     therefor
    1.00
     Ridley
    0.98
    ity
    0.98
    Act Density 0.434%

    No Known Activations