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

    Neuronpedia

    INDEX
    Explanations

    GROUP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Login
    -0.07
    Cr
    -0.06
    Manual
    -0.06
    肌
    -0.06
     رسید
    -0.06
    .pop
    -0.06
    _VERTICAL
    -0.06
     Voor
    -0.06
    プロ
    -0.06
     ของ
    -0.06
    POSITIVE LOGITS
     erotique
    0.08
     dormant
    0.07
     startIndex
    0.07
    $route
    0.07
     Athen
    0.07
    sembl
    0.07
    nesday
    0.07
     ToDo
    0.06
     butcher
    0.06
    illions
    0.06
    Act Density 0.455%

    No Known Activations