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

    Neuronpedia

    INDEX
    Explanations

    right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bron
    -0.07
     sexuality
    -0.06
    ilitating
    -0.06
    zeug
    -0.06
     technicians
    -0.06
    _xs
    -0.06
    UNT
    -0.06
    -Cs
    -0.06
    cepts
    -0.06
    파일
    -0.06
    POSITIVE LOGITS
    reh
    0.06
     keep
    0.06
    (double
    0.06
    ่ม
    0.06
    вай
    0.06
     arrang
    0.06
     Hopefully
    0.06
    911
    0.06
     Bourbon
    0.06
    edx
    0.06
    Act Density 0.107%

    No Known Activations