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

    Neuronpedia

    INDEX
    Explanations

    references to instances of "self" in programming context

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

    academic citations with ibid

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.83
    istoitu
    -0.68
    OGND
    -0.66
     snippetHide
    -0.66
    addGap
    -0.65
     createSlice
    -0.63
    parsedMessage
    -0.63
     Infórmanos
    -0.63
    :+:
    -0.61
     <<<<<<<<<<<<<<
    -0.61
    POSITIVE LOGITS
     the
    0.71
     hakim
    0.46
     data
    0.44
     komputer
    0.42
     ulica
    0.41
     cheval
    0.41
     computers
    0.41
    jenigen
    0.40
     kuli
    0.40
    ทุน
    0.40
    Act Density 0.001%

    No Known Activations