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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hud
    -0.07
     mentioned
    -0.06
    แก
    -0.06
    Dick
    -0.06
    ਯ
    -0.06
    裉
    -0.06
    _parm
    -0.06
    (workspace
    -0.06
    Sparse
    -0.06
     zale
    -0.06
    POSITIVE LOGITS
     رائع
    0.08
    щик
    0.08
     funding
    0.08
     trẻ
    0.07
    ”)
    0.07
    印发
    0.07
     적용
    0.07
    ając
    0.07
     יכול
    0.07
    la
    0.07
    Act Density 0.101%

    No Known Activations