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

    Neuronpedia

    INDEX
    Explanations

    it needs to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     simplifié
    0.46
     printr
    0.46
     indemnify
    0.45
     thicken
    0.44
     lá
    0.43
     sempl
    0.40
     unite
    0.40
     refinance
    0.40
     renseignements
    0.40
    なんか
    0.40
    POSITIVE LOGITS
    》，
    0.38
    '
    0.38
    味道
    0.37
    ⁹
    0.37
    에서
    0.36
    *
    0.36
    9
    0.36
     Gateway
    0.36
     Timeout
    0.35
    到
    0.35
    Act Density 0.000%

    No Known Activations