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

    Neuronpedia

    INDEX
    Explanations

    impact it has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ugia
    0.41
    DebugType
    0.38
    ৭০
    0.38
    ूत
    0.37
    గిన
    0.37
    leftChild
    0.36
    哳
    0.36
     devad
    0.35
     MILK
    0.35
    妫
    0.35
    POSITIVE LOGITS
    ACS
    0.42
     सामना
    0.40
    Sandy
    0.40
     Sandy
    0.40
     Tol
    0.39
    かも
    0.39
    idey
    0.39
     Estate
    0.38
     Fancy
    0.38
     Zustand
    0.37
    Act Density 0.006%

    No Known Activations