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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    programming-related syntax and structures

    np_token-act-pair-logits · gpt-4o-mini

    code or logs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -0.79
    ".
    -0.73
     CURIAM
    -0.66
     تضيفلها
    -0.65
    }';
    -0.65
     noDo
    -0.64
    OOTDTY
    -0.63
    ]";
    -0.62
    "}>
    -0.62
    SequentialGroup
    -0.60
    POSITIVE LOGITS
    .
    1.04
     =
    0.83
    =
    0.63
    [
    0.59
    ().
    0.52
    V
    0.52
    enterOuterAlt
    0.51
     also
    0.49
    ServiceModel
    0.48
    (
    0.48
    Act Density 3.489%

    No Known Activations