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

    Neuronpedia

    INDEX
    Explanations

    very strong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Chairman
    0.47
     Governance
    0.42
     قوانین
    0.41
     governance
    0.41
     Chairman
    0.40
    赞
    0.39
     ${(
    0.38
     conosci
    0.38
    👕
    0.38
    tsConfig
    0.38
    POSITIVE LOGITS
    ետ
    0.43
     extens
    0.41
     rack
    0.40
     typhoon
    0.40
     hideous
    0.39
    function
    0.39
     função
    0.38
     herb
    0.38
     fouled
    0.38
    aranja
    0.37
    Act Density 0.004%

    No Known Activations