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

    Neuronpedia

    INDEX
    Explanations

    foreign policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chai
    -0.07
    кот
    -0.07
    iode
    -0.07
     пла
    -0.07
    	strcat
    -0.06
    ulet
    -0.06
    Conversion
    -0.06
     CHILD
    -0.06
     bath
    -0.06
    _bel
    -0.06
    POSITIVE LOGITS
    .forName
    0.07
    (done
    0.06
    نسا
    0.06
    оличество
    0.06
    
    0.06
    >',↵
    0.06
     rationale
    0.06
    apg
    0.06
    >To
    0.06
     보호
    0.06
    Act Density 0.049%

    No Known Activations