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

    Neuronpedia

    INDEX
    Explanations

    aram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lara
    -0.07
     jaké
    -0.07
    regulated
    -0.06
     Weiner
    -0.06
     caves
    -0.06
     스
    -0.06
     unilateral
    -0.06
     conclusion
    -0.06
     Front
    -0.06
    559
    -0.06
    POSITIVE LOGITS
    .slice
    0.07
    '),↵
    0.06
    اءات
    0.06
     арти
    0.06
    =in
    0.06
    uploaded
    0.06
    ایی
    0.06
     entren
    0.06
    ）。↵↵
    0.06
     '''↵↵
    0.06
    Act Density 0.137%

    No Known Activations