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

    Neuronpedia

    INDEX
    Explanations

    Executable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enheim
    -0.07
    784
    -0.07
    airobi
    -0.07
    olerance
    -0.06
     облі
    -0.06
     rede
    -0.06
    ублі
    -0.06
     este
    -0.06
     Auschwitz
    -0.06
     Bangladesh
    -0.06
    POSITIVE LOGITS
     intermittent
    0.07
    لسل
    0.07
     �
    0.06
     있고
    0.06
    가격
    0.06
     لق
    0.06
    ับร
    0.06
    scar
    0.06
     تسم
    0.06
    /cop
    0.06
    Act Density 0.001%

    No Known Activations