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

    Neuronpedia

    INDEX
    Explanations

    political representatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _IE
    -0.07
     Gardner
    -0.06
    hist
    -0.06
     tej
    -0.06
    French
    -0.06
    르게
    -0.06
     ještě
    -0.06
    _tc
    -0.06
     estable
    -0.06
     attackers
    -0.06
    POSITIVE LOGITS
    0.07
     Αλ
    0.07
     Assembly
    0.07
     информа
    0.07
    (Frame
    0.06
    เสน
    0.06
    シー
    0.06
    ocity
    0.06
     amounted
    0.06
    +W
    0.06
    Act Density 0.008%

    No Known Activations