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

    Neuronpedia

    INDEX
    Explanations

    er

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descon
    -0.07
    dT
    -0.07
    犍
    -0.07
    �
    -0.07
    ertil
    -0.07
    윈
    -0.06
    傣
    -0.06
    defaultValue
    -0.06
    iropr
    -0.06
    タイ
    -0.06
    POSITIVE LOGITS
    ule
    0.07
    ("__
    0.07
    _prefix
    0.07
    ⒫
    0.07
    ("\
    0.07
    犯
    0.07
    cale
    0.07
    编剧
    0.06
    晦
    0.06
    MENTS
    0.06
    Act Density 0.182%

    No Known Activations