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

    Neuronpedia

    INDEX
    Explanations

    Which followed by payment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skele
    0.47
     permissions
    0.40
    permissions
    0.39
    𝟖
    0.39
    Loss
    0.39
     Permissions
    0.38
    Permissions
    0.38
    ContainsKey
    0.37
    ʰ
    0.37
    サイズ
    0.36
    POSITIVE LOGITS
     IBM
    0.45
    IBM
    0.41
     Scotia
    0.36
     Wat
    0.36
     المعل
    0.36
    localVar
    0.36
    मला
    0.35
     APPLE
    0.35
     siehe
    0.34
     cuộc
    0.34
    Act Density 0.012%

    No Known Activations