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

    Neuronpedia

    INDEX
    Explanations

    premises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sullivan
    -0.07
     رفت
    -0.07
    ål
    -0.07
    اظ
    -0.07
    _arr
    -0.06
    -0.06
    avail
    -0.06
    ファ
    -0.06
     또는
    -0.06
     Alla
    -0.06
    POSITIVE LOGITS
     premises
    0.18
     premise
    0.08
     confines
    0.08
    Prem
    0.08
     Prem
    0.07
     floors
    0.07
     precinct
    0.07
     remains
    0.07
     PM
    0.07
    Micro
    0.07
    Act Density 0.002%

    No Known Activations