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

    Neuronpedia

    INDEX
    Explanations

    Forum posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     odom
    -0.07
     Said
    -0.07
    <W
    -0.07
     msgs
    -0.06
     newVal
    -0.06
    े↵
    -0.06
     paddingLeft
    -0.06
    Void
    -0.06
     Extreme
    -0.06
    $model
    -0.06
    POSITIVE LOGITS
     Libert
    0.07
     blends
    0.07
    ştir
    0.06
     контролю
    0.06
    	private
    0.06
    cke
    0.06
    (admin
    0.06
    .title
    0.06
    に対
    0.06
    احت
    0.06
    Act Density 0.000%

    No Known Activations