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

    Neuronpedia

    INDEX
    Explanations

    medical school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ू
    -0.09
    �
    -0.08
     الموس
    -0.07
    vos
    -0.07
    zt
    -0.07
     barg
    -0.07
    .ID
    -0.07
    .Q
    -0.07
     disproportionate
    -0.06
     daytime
    -0.06
    POSITIVE LOGITS
    itrust
    0.06
     الدر
    0.06
    .quote
    0.06
    _Bool
    0.06
    พวกเข
    0.06
    ={{↵
    0.06
    ينة
    0.06
    owel
    0.06
     Child
    0.06
    nám
    0.06
    Act Density 0.242%

    No Known Activations