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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     матері
    -0.08
     McConnell
    -0.07
    項
    -0.07
    _SETTINGS
    -0.07
     Werk
    -0.06
     Login
    -0.06
    HI
    -0.06
     McB
    -0.06
     shore
    -0.06
     Lori
    -0.06
    POSITIVE LOGITS
    izz
    0.07
    探
    0.06
     Attend
    0.06
     disreg
    0.06
     nat
    0.06
    .Reader
    0.06
    ceb
    0.06
     pož
    0.06
    таки
    0.06
    :mysql
    0.06
    Act Density 0.034%

    No Known Activations