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

    Neuronpedia

    INDEX
    Explanations

    public restrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     survived
    0.43
     buried
    0.42
    aber
    0.41
    rep
    0.41
     seized
    0.40
     killer
    0.40
     subm
    0.39
     privacy
    0.39
     humor
    0.39
     rep
    0.38
    POSITIVE LOGITS
     रिज
    0.39
    鋯
    0.39
    CHANT
    0.39
    लिये
    0.38
    TAGE
    0.38
    𝓖
    0.38
     سير
    0.37
    苻
    0.37
    わけ
    0.37
     күз
    0.37
    Act Density 0.000%

    No Known Activations