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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     मश
    -0.07
    肯定
    -0.07
    �
    -0.06
     marty
    -0.06
    -comment
    -0.06
    ymes
    -0.06
     replies
    -0.06
     خوب
    -0.06
    .Proxy
    -0.06
    .Owner
    -0.06
    POSITIVE LOGITS
    Piece
    0.07
    elsey
    0.07
    sup
    0.06
    (...)↵
    0.06
    STREAM
    0.06
     exclusively
    0.06
    bury
    0.06
    乎
    0.06
     MODE
    0.06
    etc
    0.06
    Act Density 0.030%

    No Known Activations