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

    Neuronpedia

    INDEX
    Explanations

    most common version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cluster
    0.47
     accel
    0.45
    Cock
    0.44
    Good
    0.42
    âtre
    0.41
    Noeud
    0.41
     المخت
    0.41
    Stew
    0.41
    Accel
    0.41
    linkLabel
    0.40
    POSITIVE LOGITS
     version
    0.57
     mode
    0.53
    )/(
    0.52
    バージョン
    0.43
    兩種
    0.43
     VERSION
    0.42
     tuk
    0.42
     版本
    0.42
     tuberc
    0.42
    モード
    0.41
    Act Density 0.000%

    No Known Activations