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

    Neuronpedia

    INDEX
    Explanations

    crazy success

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ્લે
    1.50
    ріа
    1.35
    weile
    1.33
    ,|\
    1.33
    راحی
    1.33
    ဌ
    1.32
    ೆಯ
    1.32
    otypes
    1.31
     Jaan
    1.31
    athons
    1.29
    POSITIVE LOGITS
     giant
    1.19
    Giant
    0.99
    giant
    0.89
     vraag
    0.89
    comb
    0.86
     Giant
    0.85
     manure
    0.84
     mute
    0.82
    item
    0.81
    estimate
    0.80
    Act Density 0.000%

    No Known Activations