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

    Neuronpedia

    INDEX
    Explanations

    storage

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    쥐
    -0.07
     {"
    -0.07
    .prom
    -0.07
    ]
↵
    -0.07
    }],
    -0.07
    IsValid
    -0.07
    いつも
    -0.07
    一路上
    -0.07
    =@"
    -0.07
    讨厌
    -0.07
    POSITIVE LOGITS
    ********************************
    0.08
     Spot
    0.07
     Notre
    0.07
    SHA
    0.07
    해
    0.07
     Shak
    0.07
    ophe
    0.07
    oplan
    0.06
     Rotation
    0.06
     Flavor
    0.06
    Act Density 0.232%

    No Known Activations