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

    Neuronpedia

    INDEX
    Explanations

    expressions of likelihood or probability

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

    probability or likelihood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alluminio
    -0.48
     BnF
    -0.45
     suor
    -0.42
     pēc
    -0.40
     maș
    -0.38
    ReadInt
    -0.37
     što
    -0.37
     vuotta
    -0.36
     viņ
    -0.36
    ophenol
    -0.36
    POSITIVE LOGITS
     likely
    1.32
    likely
    1.24
     Likely
    1.20
    Likely
    1.16
    probable
    0.80
     Likelihood
    0.77
     probable
    0.77
     Probable
    0.76
    Likelihood
    0.75
     вероят
    0.74
    Act Density 0.013%

    No Known Activations