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

    Neuronpedia

    INDEX
    Explanations

    software development tools and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ttl
    1.31
    ป์
    1.30
     وعلى
    1.27
    ρους
    1.24
     observa
    1.20
     buzzer
    1.19
     snorkeling
    1.17
    詣
    1.16
    汅
    1.14
     Rachael
    1.11
    POSITIVE LOGITS
    ity
    1.68
    ח
    1.68
    ist
    1.62
    أ
    1.59
    ли
    1.59
    th
    1.56
    criar
    1.54
    ième
    1.52
     וע
    1.50
    ação
    1.49
    Act Density 0.000%

    No Known Activations