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

    Neuronpedia

    INDEX
    Explanations

    evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不愿
    -0.07
     seab
    -0.07
    釋
    -0.07
    ␣
    -0.07
    的心态
    -0.07
    anson
    -0.07
    _LR
    -0.07
    若
    -0.07
    .setOutput
    -0.07
    膺
    -0.07
    POSITIVE LOGITS
     Pública
    0.07
    probe
    0.07
     fused
    0.07
     rice
    0.07
    ⊛
    0.07
    ië
    0.07
     wine
    0.06
    嘭
    0.06
     clauses
    0.06
     Variable
    0.06
    Act Density 0.014%

    No Known Activations