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

    Neuronpedia

    INDEX
    Explanations

    foreign language characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     minions
    0.42
     TypeError
    0.42
     Execute
    0.41
     meno
    0.41
     weit
    0.40
     Context
    0.39
     ASCII
    0.39
     checksum
    0.38
     mutton
    0.38
     Poss
    0.37
    POSITIVE LOGITS
    ′,
    0.42
    klass
    0.41
    planetary
    0.39
    ineau
    0.39
    睬
    0.38
    ികി
    0.38
    כר
    0.38
    kina
    0.38
    গুরু
    0.37
    clair
    0.36
    Act Density 0.000%

    No Known Activations