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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    以为
    -0.07
     از
    -0.07
    175
    -0.06
    <TreeNode
    -0.06
    146
    -0.06
    叔
    -0.06
    bsolute
    -0.06
     ignores
    -0.06
    233
    -0.06
     Infos
    -0.06
    POSITIVE LOGITS
    acím
    0.07
    ‌است
    0.06
    ainties
    0.06
     gön
    0.06
     Bitcoin
    0.06
    eatures
    0.06
    Exercise
    0.06
     domácí
    0.06
     causing
    0.06
     labelText
    0.06
    Act Density 0.012%

    No Known Activations