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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (slot
    -0.08
     Sign
    -0.07
     foul
    -0.07
     Fou
    -0.07
     believers
    -0.07
     рек
    -0.06
    Stephen
    -0.06
     doubt
    -0.06
    David
    -0.06
    Pal
    -0.06
    POSITIVE LOGITS
    ')==
    0.07
    ิป
    0.06
    ениями
    0.06
    ansi
    0.06
    igits
    0.06
    pendicular
    0.06
     ise
    0.06
    sville
    0.06
    ､_
    0.06
     UB
    0.06
    Act Density 0.071%

    No Known Activations