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

    Neuronpedia

    INDEX
    Explanations

    void methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    amment
    0.41
    yte
    0.41
    ownie
    0.38
    သွယ်
    0.38
     switcher
    0.37
     encomenda
    0.37
    apper
    0.36
    رآ
    0.36
    elleen
    0.36
    乐观
    0.36
    POSITIVE LOGITS
    void
    1.05
     void
    0.96
     voids
    0.71
     awake
    0.64
     Void
    0.63
     Awake
    0.59
     Update
    0.56
     awoke
    0.55
    update
    0.53
    Update
    0.52
    Act Density 0.009%

    No Known Activations