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

    Neuronpedia

    INDEX
    Explanations

    presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featured
    1.47
     menang
    1.44
    ම
    1.43
     очередь
    1.40
    "",
    1.36
    foundland
    1.31
    istic
    1.29
    ंती
    1.29
    است
    1.28
    "${
    1.28
    POSITIVE LOGITS
    ოტ
    1.61
    డ్
    1.59
    𝒔
    1.59
    ляма
    1.54
     ليس
    1.52
    і
    1.51
    ures
    1.51
    чей
    1.46
    हे
    1.46
    يں
    1.44
    Act Density 0.000%

    No Known Activations