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

    Neuronpedia

    INDEX
    Explanations

    job skills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predictor
    -0.06
     learns
    -0.06
    ，则
    -0.06
     tensor
    -0.06
     gift
    -0.06
     notice
    -0.06
    午
    -0.06
     induce
    -0.06
     visited
    -0.06
     shower
    -0.05
    POSITIVE LOGITS
    ῆ
    0.07
    ersiz
    0.07
     генера
    0.07
    дат
    0.07
     koc
    0.07
    liğin
    0.07
    ]+
    0.07
     Ingen
    0.07
    -through
    0.06
     Phong
    0.06
    Act Density 0.041%

    No Known Activations