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

    Neuronpedia

    INDEX
    Explanations

    code/data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ogui
    -0.07
    Pts
    -0.06
     diary
    -0.06
    ″
    -0.06
    .wall
    -0.06
     philosoph
    -0.06
     Exhibition
    -0.06
     persist
    -0.06
    学会
    -0.06
    dos
    -0.06
    POSITIVE LOGITS
    ...</
    0.06
    сыл
    0.06
     соответ
    0.06
     İşte
    0.06
    last
    0.06
    ließ
    0.06
     Lomb
    0.06
    xfd
    0.05
     Levitra
    0.05
    .Usuario
    0.05
    Act Density 0.175%

    No Known Activations