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

    Neuronpedia

    INDEX
    Explanations

    tackle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    babel
    -0.08
    otion
    -0.07
    Georgia
    -0.07
    镁
    -0.07
    损
    -0.07
     bob
    -0.07
     seasoned
    -0.07
    ₊
    -0.07
    Input
    -0.07
    乐队
    -0.07
    POSITIVE LOGITS
     halves
    0.07
    ꦔ
    0.06
     wanted
    0.06
    печат
    0.06
    تقلي
    0.06
     hard
    0.06
     רי
    0.06
    𩽾
    0.06
    䥽
    0.06
    솬
    0.06
    Act Density 0.004%

    No Known Activations