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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to inverse functions and probability

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

    inverse concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    躇
    -0.65
    étoit
    -0.57
     Bewußt
    -0.54
     Theſe
    -0.53
    paravant
    -0.53
    holiday
    -0.52
     queſta
    -0.51
    chromedriver
    -0.51
    Mereka
    -0.50
     pertenecen
    -0.50
    POSITIVE LOGITS
     inverse
    0.94
     Inverse
    0.84
    Inverse
    0.79
    inverse
    0.77
    }^{-
    0.57
     inversa
    0.57
     OFDb
    0.56
     Inver
    0.54
     }^{-
    0.54
    ^{-
    0.52
    Act Density 0.023%

    No Known Activations