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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ビ
    -0.08
     Ming
    -0.07
    _algorithm
    -0.07
    ン�
    -0.07
    ken
    -0.07
    .mask
    -0.07
     Hat
    -0.06
    娘
    -0.06
    Mir
    -0.06
    าร
    -0.06
    POSITIVE LOGITS
     WX
    0.08
     lsp
    0.07
    inium
    0.06
     $__
    0.06
    真是
    0.06
     maneu
    0.06
    acion
    0.06
     sextreffen
    0.06
     Beaut
    0.06
    typeorm
    0.06
    Act Density 0.064%

    No Known Activations