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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -'.$
    -0.07
    /connection
    -0.06
    chu
    -0.06
    ря
    -0.06
     eh
    -0.06
    _TYPE
    -0.06
     facets
    -0.06
    749
    -0.06
     beden
    -0.06
     trades
    -0.06
    POSITIVE LOGITS
    规划
    0.07
    .userAgent
    0.06
    งก
    0.06
    智能
    0.06
    먹
    0.06
     immun
    0.06
     MIS
    0.06
    γ
    0.06
     MULT
    0.06
     γ
    0.06
    Act Density 0.002%

    No Known Activations