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

    Neuronpedia

    INDEX
    Explanations

    UNIVERSITY OF, Rite of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.56
    v
    0.52
    D
    0.52
     March
    0.51
    R
    0.51
    V
    0.50
    From
    0.49
    Bl
    0.49
     Journal
    0.48
    B
    0.47
    POSITIVE LOGITS
    Concerning
    0.51
    ➸
    0.49
    нити
    0.49
    蠻
    0.49
    textepsilon
    0.48
     生地
    0.47
    olí
    0.47
     භාවිත
    0.47
    meer
    0.46
    Emit
    0.46
    Act Density 0.000%

    No Known Activations