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

    Neuronpedia

    INDEX
    Explanations

    API delete endpoints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꗕ
    0.93
     +#+#+#+#+#+
    0.93
    𒉕
    0.93
    Polynucleaires
    0.93
    𒂤
    0.93
     துய்யமணி
    0.93
    𒀣
    0.93
    𒅊
    0.92
     +#+#+#
    0.92
    𒊖
    0.92
    POSITIVE LOGITS
     ChatGPT
    0.74
     bir
    0.69
     que
    0.65
     openai
    0.65
     like
    0.64
     como
    0.62
     someone
    0.60
     just
    0.59
    0.59
     for
    0.58
    Act Density 0.267%

    No Known Activations