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

    Neuronpedia

    INDEX
    Explanations

    sub

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.82
    ftagPool
    -0.75
    oredCriteria
    -0.71
     Sub
    -0.70
     sub
    -0.69
    awtextra
    -0.66
    GOTREF
    -0.62
     Tran
    -0.59
    UIControlState
    -0.59
     Ab
    -0.59
    POSITIVE LOGITS
    InRange
    0.46
    contr
    0.46
    bilecek
    0.43
    (!_
    0.40
    urt
    0.40
     sembler
    0.40
    一口气
    0.39
    contract
    0.38
    sie
    0.38
    Bernhard
    0.38
    Act Density 0.013%

    No Known Activations