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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating clarity or obviousness

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

    evident

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aé
    -0.53
     Bowles
    -0.53
    IntoConstraints
    -0.51
     obé
    -0.49
     anſ
    -0.49
     juſ
    -0.49
     tranſ
    -0.48
     auroit
    -0.48
     jurisdic
    -0.47
     abur
    -0.47
    POSITIVE LOGITS
     evident
    1.73
    evident
    1.58
    vident
    1.02
    Evid
    0.98
     evidently
    0.98
     Evidently
    0.97
    evid
    0.91
     evidente
    0.82
     Evid
    0.75
     evidenced
    0.71
    Act Density 0.006%

    No Known Activations