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

    Neuronpedia

    INDEX
    Explanations

    negative numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0
    1.71
    ૦
    1.52
    6
    1.38
    م
    1.35
    راہیم
    1.30
    life
    1.30
     organize
    1.28
    గ
    1.27
    s
    1.27
     सैन्य
    1.26
    POSITIVE LOGITS
    .
    1.28
     laughable
    1.10
     laparoscopic
    1.08
     piace
    1.05
     ludicrous
    1.05
    şik
    1.05
    ן
    1.05
    йна
    1.04
     negligible
    1.03
     that
    1.02
    Act Density 3.230%

    No Known Activations