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

    Neuronpedia

    INDEX
    Explanations

    zip followed by parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    itization
    1.52
    imiento
    1.44
     hens
    1.43
     inhalation
    1.42
     BadRequest
    1.39
     conda
    1.36
    ᅣ
    1.36
     tensors
    1.36
     DQN
    1.35
     onItem
    1.33
    POSITIVE LOGITS
    y
    1.54
    м
    1.42
    эс
    1.31
    此同时
    1.26
    ম্বা
    1.22
    čil
    1.14
    jpe
    1.13
     уж
    1.10
     emas
    1.09
     campagna
    1.09
    Act Density 0.000%

    No Known Activations