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

    Neuronpedia

    INDEX
    Explanations

    countries and nationalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    0.64
     patitth
    0.55
     άνθρω
    0.54
    ção
    0.49
    iéndose
    0.47
     orgánica
    0.47
    지에
    0.46
    i
    0.46
    iť
    0.46
    ul
    0.46
    POSITIVE LOGITS
     be
    0.52
    是
    0.46
            
    0.46
     I
    0.45
    I
    0.45
    ру
    0.45
    స్
    0.44
    ON
    0.44
    س
    0.43
    は
    0.42
    Act Density 0.992%

    No Known Activations