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

    Neuronpedia

    INDEX
    Explanations

    specific names, likely related to authors or researchers in formal citations

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

    Single uppercase letters

    np_acts-logits-general · gemini-2.0-flash

    initials followed by a period

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tartalomajánló
    -1.08
     typelib
    -0.80
    GEBURTSDATUM
    -0.72
     Biôgrafia
    -0.67
    #+#
    -0.65
    setVerticalGroup
    -0.64
    oubliez
    -0.63
     snippetHide
    -0.62
     validamos
    -0.61
    WriteTagHelper
    -0.60
    POSITIVE LOGITS
    gogo
    0.54
    født
    0.46
    addressed
    0.46
     Jr
    0.44
     granos
    0.44
     Arrays
    0.43
    Jr
    0.43
    utivo
    0.43
     alemão
    0.43
     للمعارف
    0.43
    Act Density 0.060%

    No Known Activations