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

    Neuronpedia

    INDEX
    Explanations

    various phrases and their definitions or contexts

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

    phrase or expression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̈́
    -0.54
    ErrUnexpectedEOF
    -0.50
    WarningLevel
    -0.42
     compleanno
    -0.41
    хьтан
    -0.40
    Goodness
    -0.39
    Biographies
    -0.39
     obiettivo
    -0.38
     Normdatei
    -0.38
    ollectionView
    -0.37
    POSITIVE LOGITS
     phrase
    1.06
     phrases
    1.02
     Phrase
    0.92
     Phrases
    0.88
    phrase
    0.79
     frase
    0.74
     term
    0.73
    Phrase
    0.72
    phrases
    0.71
     terms
    0.66
    Act Density 0.071%

    No Known Activations