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

    Neuronpedia

    INDEX
    Explanations

    optional clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    나
    0.46
    เร
    0.45
    exploration
    0.44
    니
    0.43
    โน
    0.42
     Каждый
    0.42
    ziemy
    0.42
    ᠰ
    0.42
     ניתן
    0.42
     クリスマス
    0.41
    POSITIVE LOGITS
     otra
    0.46
     autre
    0.46
     deceive
    0.45
     ajj
    0.45
     دیگه
    0.45
     falsa
    0.44
     conferencia
    0.42
     perfe
    0.42
     disagreed
    0.42
    电话
    0.41
    Act Density 0.005%

    No Known Activations