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

    Neuronpedia

    INDEX
    Explanations

    image filenames and related URL paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    File extensions or image names

    np_acts-logits-general · gemini-2.0-flash

    file names and paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >")
    -0.69
    (");
    -0.68
    :✨
    -0.66
    !):
    -0.65
    ="")
    -0.64
    ?):
    -0.64
     protoimpl
    -0.63
    ://"
    -0.63
     CreateTagHelper
    -0.63
    ?";
    -0.63
    POSITIVE LOGITS
     FINAL
    0.95
    _
    0.94
    final
    0.93
    FINAL
    0.85
    _-_
    0.84
     final
    0.80
    Final
    0.76
     Final
    0.76
     副本
    0.68
    _(
    0.67
    Act Density 0.507%

    No Known Activations