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

    Neuronpedia

    INDEX
    Explanations

    scientific and mathematical notation

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     +
    -2.14
    +
    -1.71
     $+$
    -1.52
     plus
    -1.51
     $+
    -1.50
     →
    -1.30
     (+
    -1.30
     =
    -1.30
    plus
    -1.28
     плюс
    -1.27
    POSITIVE LOGITS
    ,:);
    0.72
    ))){
    0.68
    --){
    0.66
    ]");
    0.66
    )";
    0.65
    ;");
    0.65
    */;
    0.64
    ?");
    0.64
    ;';
    0.64
    ]`
    0.63
    Act Density 14.291%

    No Known Activations