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

    Neuronpedia

    INDEX
    Explanations

    developers invest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    સ્થા
    0.42
     crazy
    0.40
    wedd
    0.39
    Yale
    0.38
     rags
    0.38
     ጨ
    0.37
     portray
    0.37
    >..\
    0.37
     detecting
    0.37
     fledgling
    0.37
    POSITIVE LOGITS
    preferred
    0.43
     optionally
    0.42
    添付
    0.41
     preferred
    0.41
     Preferred
    0.40
     Secured
    0.39
     secures
    0.38
     স্বামীকে
    0.38
    ники
    0.38
    钣
    0.37
    Act Density 0.001%

    No Known Activations