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

    Neuronpedia

    INDEX
    Explanations

    content repurposing subscription

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aneu
    0.82
    PlatformToolset
    0.80
     hydrazine
    0.80
     traw
    0.78
    BleStatus
    0.77
    Wow
    0.77
     hallways
    0.76
     coffers
    0.75
     legions
    0.75
    ┏
    0.74
    POSITIVE LOGITS
    em
    0.84
    ef
    0.83
    ic
    0.82
    id
    0.81
    in
    0.80
    il
    0.80
    ischen
    0.79
    ur
    0.77
    isch
    0.75
    ous
    0.74
    Act Density 0.000%

    No Known Activations