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

    Neuronpedia

    INDEX
    Explanations

    code, errors, documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indebted
    -0.07
     Gundam
    -0.07
    .rate
    -0.07
    }},↵
    -0.06
     Angel
    -0.06
    Whole
    -0.06
     Ron
    -0.06
     seasoned
    -0.06
     gang
    -0.06
     Shader
    -0.06
    POSITIVE LOGITS
     view
    0.07
    明媚
    0.07
    (instance
    0.07
     converse
    0.07
     vs
    0.07
    _increase
    0.07
    _guess
    0.06
    斗志
    0.06
    adero
    0.06
    不断增强
    0.06
    Act Density 0.077%

    No Known Activations