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

    Neuronpedia

    INDEX
    Explanations

    html tags and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     diskut
    0.66
     superfície
    0.63
     vendido
    0.62
     ର
    0.62
    this
    0.61
    }}}{
    0.61
     größere
    0.59
    7
    0.59
     svenska
    0.59
    ны
    0.58
    POSITIVE LOGITS
    :
    0.72
    ש
    0.65
     out
    0.64
     ibid
    0.62
     AND
    0.59
     or
    0.58
     Trotsky
    0.58
    ：
    0.58
    .:
    0.57
     alluring
    0.57
    Act Density 0.088%

    No Known Activations