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

    Neuronpedia

    INDEX
    Explanations

    We

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    くの
    -0.06
     preseason
    -0.06
     Reliable
    -0.06
     �
    -0.06
     Př
    -0.06
    ってきた
    -0.06
     Asians
    -0.06
    ยนแปลง
    -0.06
    _->
    -0.06
    少し
    -0.06
    POSITIVE LOGITS
     tall
    0.07
    лата
    0.07
     inhabit
    0.06
     allele
    0.06
    WithType
    0.06
    ]])↵↵
    0.06
    _attempts
    0.06
     Colin
    0.06
     rather
    0.06
     "↵↵
    0.06
    Act Density 0.050%

    No Known Activations