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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _texture
    -0.08
    DLL
    -0.08
     planets
    -0.07
     contrôle
    -0.07
    控
    -0.07
     Pattern
    -0.07
    洞
    -0.07
     Wait
    -0.07
    焦点
    -0.07
    地球
    -0.07
    POSITIVE LOGITS
    ⓖ
    0.07
    Reward
    0.07
    (guess
    0.06
    幸好
    0.06
    墼
    0.06
    韭
    0.06
    ously
    0.06
    一会
    0.06
    츕
    0.06
    HER
    0.06
    Act Density 0.006%

    No Known Activations