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

    Neuronpedia

    INDEX
    Explanations

    inflammatory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    един
    -0.07
     deeds
    -0.07
    итив
    -0.06
     마지막
    -0.06
    طل
    -0.06
    바이
    -0.06
     unanim
    -0.06
    nar
    -0.06
    âr
    -0.06
    ين
    -0.06
    POSITIVE LOGITS
    Chicago
    0.07
    �
    0.07
    rob
    0.07
    />
    0.07
    Dialogue
    0.07
     turist
    0.06
     generates
    0.06
     six
    0.06
    .isdigit
    0.06
     Rub
    0.06
    Act Density 0.016%

    No Known Activations