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

    Neuronpedia

    INDEX
    Explanations

    political history

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Uk
    -0.07
    POP
    -0.06
    .***
    -0.06
     Uz
    -0.06
    >B
    -0.06
     ülke
    -0.06
     conscious
    -0.06
    omal
    -0.06
    .id
    -0.06
    姑
    -0.06
    POSITIVE LOGITS
    -St
    0.06
    (age
    0.06
     ανά
    0.06
    pg
    0.06
     гри
    0.06
    ={↵
    0.06
    (styles
    0.06
    ([]*
    0.06
     사항
    0.06
     TOUCH
    0.06
    Act Density 0.061%

    No Known Activations