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

    Neuronpedia

    INDEX
    Explanations

    familial relationships and lineage

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

    Words/names followed by a name

    np_acts-logits-general · gemini-2.0-flash

    names and contraband

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MLLoader
    -0.83
    êque
    -0.69
    ragamo
    -0.65
    +#+#
    -0.60
    ÈRE
    -0.60
     OMIT
    -0.59
     Guggenheim
    -0.59
     виправивши
    -0.58
    WarningLevel
    -0.58
    LookAnd
    -0.57
    POSITIVE LOGITS
     tattoos
    0.53
     Tribal
    0.53
     tattoo
    0.51
    Tribal
    0.50
     methamphetamine
    0.49
     Facebook
    0.49
     payday
    0.48
     tattooed
    0.47
    oneofs
    0.47
    Facebook
    0.46
    Act Density 0.204%

    No Known Activations