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

    Neuronpedia

    INDEX
    Explanations

    comparisons and contrasts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _percent
    -0.08
     initWithFrame
    -0.08
     /\.
    -0.07
     TObject
    -0.07
    ⌣
    -0.07
    特派
    -0.07
    .forChild
    -0.07
    突出问题
    -0.07
     handleClick
    -0.07
    ()?;↵
    -0.07
    POSITIVE LOGITS
    归
    0.07
    嘉
    0.07
     misogyn
    0.07
    $out
    0.07
    imp
    0.07
    OG
    0.07
     �
    0.07
     rooms
    0.06
    uns
    0.06
    Day
    0.06
    Act Density 0.087%

    No Known Activations