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

    Neuronpedia

    INDEX
    Explanations

    -xs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BMI
    -0.08
    ']}</
    -0.07
    mary
    -0.07
    Þ
    -0.07
     рус
    -0.06
    	copy
    -0.06
    _estimate
    -0.06
    )&&
    -0.06
     rotation
    -0.06
    833
    -0.06
    POSITIVE LOGITS
     xs
    0.08
    s
    0.07
    vs
    0.07
    xs
    0.06
    .fs
    0.06
    si
    0.06
    -xs
    0.06
     Ins
    0.06
     DS
    0.06
     Вс
    0.06
    Act Density 0.001%

    No Known Activations