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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avi
    -0.07
    spacing
    -0.07
     ขนาด
    -0.06
     Vapor
    -0.06
     �
    -0.06
     Tri
    -0.06
    ิกายน
    -0.06
    decor
    -0.06
     пен
    -0.06
    _xyz
    -0.06
    POSITIVE LOGITS
     示
    0.06
    capture
    0.06
    .forEach
    0.06
     Wort
    0.06
    Ξ
    0.06
    UPPORT
    0.06
    What
    0.06
    .runners
    0.06
     ハ
    0.06
    :h
    0.06
    Act Density 0.001%

    No Known Activations