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

    Neuronpedia

    INDEX
    Explanations

    partial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testosterone
    -0.08
    ienia
    -0.08
     robust
    -0.08
     Humph
    -0.07
     होते
    -0.07
     instructional
    -0.07
    IFS
    -0.07
     prominently
    -0.07
     Dale
    -0.07
     dramatically
    -0.07
    POSITIVE LOGITS
     初始化
    0.09
    .binary
    0.08
    .xaml
    0.08
     页
    0.08
     satisf
    0.08
     Pane
    0.08
     引
    0.08
     shock
    0.07
     unan
    0.07
     Initialized
    0.07
    Act Density 0.002%

    No Known Activations