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

    Neuronpedia

    INDEX
    Explanations

    prepositions/commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ዝ
    -0.07
    .GREEN
    -0.07
    完整
    -0.07
    첮
    -0.06
     Sized
    -0.06
    _git
    -0.06
     Parl
    -0.06
    法治
    -0.06
    舴
    -0.06
     xứ
    -0.06
    POSITIVE LOGITS
    Expiration
    0.08
    ections
    0.08
    jobs
    0.07
     gate
    0.07
     prohib
    0.07
    幕墙
    0.07
     Destruction
    0.07
     regulation
    0.07
    _eth
    0.07
    法定
    0.07
    Act Density 0.003%

    No Known Activations