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

    Neuronpedia

    INDEX
    Explanations

    nan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     erection
    -0.08
    ิต
    -0.06
    파트
    -0.06
    اكن
    -0.06
    рії
    -0.06
    _Debug
    -0.06
    ایع
    -0.06
     Mounted
    -0.06
     特
    -0.06
    он
    -0.06
    POSITIVE LOGITS
    チーム
    0.08
     mor
    0.07
     stereo
    0.07
     Peer
    0.07
     Tide
    0.06
    (core
    0.06
    bol
    0.06
     roam
    0.06
     rab
    0.06
    olucion
    0.06
    Act Density 0.332%

    No Known Activations