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

    Neuronpedia

    INDEX
    Explanations

    uses-permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     weak
    0.40
    dj
    0.39
     comes
    0.39
    ប្រស
    0.38
     zealous
    0.37
     prevail
    0.37
     ይመ
    0.37
     distract
    0.37
    (())
    0.36
     preval
    0.36
    POSITIVE LOGITS
     consumir
    0.40
     chơi
    0.40
    ynit
    0.38
    شف
    0.38
    จทย์
    0.37
     CHROM
    0.37
    UseVisualStyle
    0.36
     ventures
    0.36
     Kan
    0.35
    মহ
    0.35
    Act Density 0.001%

    No Known Activations