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

    Neuronpedia

    INDEX
    Explanations

    even

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _mime
    -0.07
     healed
    -0.07
     Hd
    -0.07
    Invite
    -0.07
    分散
    -0.06
     uid
    -0.06
     spare
    -0.06
    辞职
    -0.06
    ᗨ
    -0.06
    겋
    -0.06
    POSITIVE LOGITS
     detects
    0.07
     meant
    0.07
    -syntax
    0.07
    엥
    0.07
    PubMed
    0.06
    !("{}",
    0.06
     significance
    0.06
    	table
    0.06
     recip
    0.06
    意义
    0.06
    Act Density 0.004%

    No Known Activations