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

    Neuronpedia

    INDEX
    Explanations

    the Cyrillic letter 'с' in varying contexts and frequencies

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

    prepositions and connectors across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    endregion
    -0.66
    rungsseite
    -0.48
     tjen
    -0.48
    ftance
    -0.47
     Erscheinung
    -0.47
    ActionMode
    -0.46
     aikana
    -0.46
    المكان
    -0.45
    Viited
    -0.44
    DeleteBehavior
    -0.44
    POSITIVE LOGITS
     с
    0.84
     with
    0.66
     עם
    0.66
    with
    0.62
     With
    0.60
     WITH
    0.59
    With
    0.53
     From
    0.52
     із
    0.52
    dengan
    0.51
    Act Density 0.008%

    No Known Activations