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

    Neuronpedia

    INDEX
    Explanations

    contractions and informal expressions of negation

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

    the EU or lyrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.66
    rungsseite
    -0.64
     ainfi
    -0.60
    ftagPool
    -0.59
    ImageContext
    -0.58
     autorytatywna
    -0.57
    efois
    -0.54
    bootstrapcdn
    -0.53
     betweenstory
    -0.53
     esportivo
    -0.53
    POSITIVE LOGITS
     lyrics
    0.51
     Eu
    0.41
     tissue
    0.40
     cre
    0.39
     scri
    0.39
     Absol
    0.38
     Colle
    0.38
     Nic
    0.37
    Eu
    0.36
    NOPQRST
    0.36
    Act Density 0.034%

    No Known Activations