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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives and expressions indicating admiration or approval

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

    positive evaluations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Penelitian
    -0.36
     suyo
    -0.36
    iastes
    -0.36
    mainan
    -0.34
    atuan
    -0.33
    mitian
    -0.31
     alguien
    -0.30
     fotógrafo
    -0.30
     policiers
    -0.30
     veckan
    -0.29
    POSITIVE LOGITS
    AndEndTag
    0.59
    protoimpl
    0.59
    LookAnd
    0.57
     CallOverrides
    0.55
    printStackTrace
    0.55
    ///</
    0.54
     CreateTagHelper
    0.54
     Majefty
    0.53
     onOptions
    0.52
     propOrder
    0.52
    Act Density 0.004%

    No Known Activations