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

    Neuronpedia

    INDEX
    Explanations

    gender

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LEAN
    -0.07
     hijos
    -0.06
    _temp
    -0.06
     disadv
    -0.06
     Polo
    -0.06
    yield
    -0.06
    /*@
    -0.06
     củ
    -0.06
     theatrical
    -0.06
    传
    -0.06
    POSITIVE LOGITS
     předsed
    0.06
    ابة
    0.06
     vids
    0.06
    _STYLE
    0.06
    .onload
    0.06
     vowed
    0.06
    .angle
    0.06
     instantly
    0.06
     Arrange
    0.06
    sPid
    0.05
    Act Density 0.005%

    No Known Activations