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

    Neuronpedia

    INDEX
    Explanations

    dialogue from fiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PIX
    -0.07
     ışı
    -0.06
     echoing
    -0.06
     Tells
    -0.06
     подав
    -0.06
     grö
    -0.06
    ッシュ
    -0.06
     gleich
    -0.06
    atég
    -0.06
     redd
    -0.06
    POSITIVE LOGITS
     sve
    0.07
     plummet
    0.07
    SignIn
    0.07
     dont
    0.07
    rió
    0.06
    _RA
    0.06
    ovatel
    0.06
    session
    0.06
    ´t
    0.06
     Observer
    0.06
    Act Density 0.065%

    No Known Activations