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

    Neuronpedia

    INDEX
    Explanations

    expressions of certainty or completion

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

    already

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    がち
    -0.37
    =".
    -0.36
     goals
    -0.35
     CAM
    -0.35
    kam
    -0.35
    "?>
    -0.35
    ない
    -0.34
     cam
    -0.34
    POC
    -0.34
    di
    -0.34
    POSITIVE LOGITS
     уже
    1.02
     już
    1.02
     вже
    0.98
     Уже
    0.92
    Уже
    0.89
     כבר
    0.87
     уж
    0.85
     már
    0.84
     už
    0.80
     artık
    0.72
    Act Density 0.003%

    No Known Activations