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

    Neuronpedia

    INDEX
    Explanations

    label

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .shell
    -0.07
    中学
    -0.07
    SingleNode
    -0.07
     výj
    -0.06
     varios
    -0.06
    Iteration
    -0.06
     Stones
    -0.06
    айд
    -0.06
     운영자
    -0.06
    “And
    -0.06
    POSITIVE LOGITS
     scoff
    0.07
     zastup
    0.06
     XB
    0.06
     tipping
    0.06
    -drive
    0.06
     treated
    0.06
     cliff
    0.06
     abol
    0.06
    liest
    0.06
     вищ
    0.06
    Act Density 0.001%

    No Known Activations