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

    Neuronpedia

    INDEX
    Explanations

    airdrop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inducted
    0.58
     IRA
    0.55
    KSI
    0.55
     Slayer
    0.54
     EDC
    0.54
     άνθρω
    0.54
     PSO
    0.54
     anarchist
    0.54
     unassuming
    0.53
    ﾓ
    0.53
    POSITIVE LOGITS
    in
    0.89
    h
    0.82
    n
    0.76
    𝚎
    0.75
    는
    0.73
    s
    0.73
    ed
    0.71
    ing
    0.70
    eq
    0.68
    alter
    0.66
    Act Density 0.001%

    No Known Activations