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

    Neuronpedia

    INDEX
    Explanations

    BI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ũ
    -0.07
    NSNotification
    -0.07
    ưỡ
    -0.07
     either
    -0.06
    奶油
    -0.06
     fuera
    -0.06
     altın
    -0.06
    检察
    -0.06
    悪
    -0.06
     \(
    -0.06
    POSITIVE LOGITS
     refl
    0.08
    _personal
    0.08
     McKin
    0.07
     defin
    0.07
    $self
    0.07
    ידה
    0.07
    _handle
    0.07
    ሚ
    0.07
    镗
    0.07
    	handle
    0.07
    Act Density 0.005%

    No Known Activations