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

    Neuronpedia

    INDEX
    Explanations

    US townships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    佺
    -0.08
    agma
    -0.07
    免税
    -0.07
    嘏
    -0.07
    alan
    -0.06
    ḏ
    -0.06
    encode
    -0.06
    ox
    -0.06
    찌
    -0.06
    Num
    -0.06
    POSITIVE LOGITS
    ~~~~
    0.08
     треб
    0.08
     hired
    0.07
     THERE
    0.07
    扭曲
    0.07
    _billing
    0.07
    Hell
    0.07
    ሚ
    0.07
    ┘
    0.07
     losing
    0.06
    Act Density 0.004%

    No Known Activations