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

    Neuronpedia

    INDEX
    Explanations

    Debian

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Auditor
    -0.08
    .BorderFactory
    -0.07
     Nimbus
    -0.07
     engraved
    -0.07
    殛
    -0.07
    _first
    -0.07
    _All
    -0.07
    _mount
    -0.07
    OCUS
    -0.06
    ἠ
    -0.06
    POSITIVE LOGITS
     historia
    0.08
    发表了
    0.07
    יזם
    0.07
    ')],↵
    0.07
    <?↵
    0.07
     contrad
    0.07
    [string
    0.06
    ケア
    0.06
     }}>
    0.06
    往年
    0.06
    Act Density 0.001%

    No Known Activations