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

    Neuronpedia

    INDEX
    Explanations

    takes a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    besiege
    0.54
    RMSE
    0.49
     проблема
    0.49
     был
    0.49
     oxidize
    0.48
    榫
    0.47
     ಟ
    0.46
     soooo
    0.46
    ñones
    0.46
     ставкалары
    0.45
    POSITIVE LOGITS
    P
    0.51
    S
    0.49
    行
    0.48
     Orlando
    0.47
    v
    0.46
    g
    0.46
     Section
    0.45
    س
    0.45
     Nap
    0.45
     College
    0.45
    Act Density 0.001%

    No Known Activations