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

    Neuronpedia

    INDEX
    Explanations

    syntax for filenames and labels in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ++){
    0.62
    "){
    0.58
    ')){
    0.52
     }}{
    0.51
     ){
    0.49
    ]++;
    0.48
     });
    0.48
    ")){
    0.47
    '){
    0.47
     NULL
    0.47
    POSITIVE LOGITS
    ["
    1.14
    ['
    1.13
    [-
    1.06
    [:
    1.05
    [:]
    1.05
    [:,
    0.92
    [:-
    0.92
    [['
    0.87
    [
    0.85
    [::-
    0.85
    Act Density 1.298%

    No Known Activations