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

    Neuronpedia

    INDEX
    Explanations

    occurrences of special characters and escape sequences

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

    Preceding certain lowercase letters

    np_acts-logits-general · gemini-2.0-flash

    birthplace and origin information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.58
    abestanden
    -0.57
    arakhand
    -0.57
    NewReader
    -0.55
    intellij
    -0.54
    CppCodeGen
    -0.54
    WebVitals
    -0.53
    Rhestr
    -0.53
    :✨
    -0.53
    prnewswire
    -0.52
    POSITIVE LOGITS
     />\
    0.51
     <<<<<<<<<<<<<<
    0.49
     RequestMethod
    0.48
     estri
    0.47
    Aid
    0.46
     Arta
    0.45
    Tetapi
    0.44
    heber
    0.44
    Lycka
    0.44
     Privacidad
    0.43
    Act Density 0.095%

    No Known Activations