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

    Neuronpedia

    INDEX
    Explanations

    . The

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varies
    0.41
     சார்ந்த
    0.38
     schme
    0.38
     hastened
    0.38
     commensurate
    0.37
     subscrib
    0.36
     unapolog
    0.36
    ㅈ
    0.35
     ожи
    0.34
     konusunda
    0.34
    POSITIVE LOGITS
    一张
    0.36
    虽然
    0.36
    绾
    0.36
    ：
    0.35
     subdir
    0.35
    ই
    0.35
     Pasta
    0.34
     unsightly
    0.34
    দীর্ঘ
    0.34
    Kum
    0.34
    Act Density 0.000%

    No Known Activations