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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _PUS
    -0.06
    G
    -0.06
     Minute
    -0.06
     Attached
    -0.06
     Course
    -0.06
    ランド
    -0.06
     tand
    -0.06
    lst
    -0.06
    шло
    -0.06
     Generator
    -0.06
    POSITIVE LOGITS
     tokenId
    0.07
    Canadian
    0.07
     ई
    0.06
    "url
    0.06
     θε
    0.06
     injust
    0.06
     Dez
    0.06
    getPath
    0.06
    ável
    0.06
    ############################################################
    0.06
    Act Density 0.005%

    No Known Activations