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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /L
    -0.07
    ỷ
    -0.07
     Patch
    -0.07
     scores
    -0.06
    �
    -0.06
     recap
    -0.06
    564
    -0.06
    巧
    -0.06
    -fat
    -0.06
     nucle
    -0.06
    POSITIVE LOGITS
     \/
    0.07
    perate
    0.07
    .resource
    0.06
     Conj
    0.06
    isNaN
    0.06
     manuscripts
    0.06
     addTarget
    0.06
     Automatically
    0.06
     ผล
    0.06
    飲
    0.06
    Act Density 0.003%

    No Known Activations