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

    Neuronpedia

    INDEX
    Explanations

    highly recommended

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    2.41
    tanto
    2.41
    tive
    2.37
    iune
    2.25
    tions
    2.25
    רץ
    2.22
    aas
    2.19
    पचारिक
    2.14
     jdbcTemplate
    2.11
    aient
    2.07
    POSITIVE LOGITS
    匐
    1.83
    rrggbb
    1.79
     mendek
    1.75
    ליך
    1.73
     interessiert
    1.71
    쳐
    1.69
    GetAxis
    1.68
    핑
    1.68
    ˶
    1.67
    ㅍ
    1.67
    Act Density 0.238%

    No Known Activations