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

    Neuronpedia

    INDEX
    Explanations

    bleeding, sever, prop bets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CHEMISTRY
    0.46
     હંમે
    0.44
    𐰖
    0.44
    ILITY
    0.42
     CHAIRMAN
    0.42
    ontrol
    0.41
     ತೊ
    0.41
    夷
    0.41
     بڑھ
    0.40
     अदानी
    0.40
    POSITIVE LOGITS
    Kub
    0.43
     amused
    0.42
    Ko
    0.40
     anteced
    0.39
     disturbances
    0.38
    雲
    0.38
     Kub
    0.38
     precedents
    0.38
    kc
    0.37
    ڤ
    0.36
    Act Density 0.002%

    No Known Activations