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

    Neuronpedia

    INDEX
    Explanations

    links to developers and tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     A
    0.28
    3
    0.27
     T
    0.27
     temps
    0.27
     Wood
    0.27
     Blood
    0.27
     The
    0.26
     Tu
    0.26
     St
    0.26
     Power
    0.26
    POSITIVE LOGITS
    ។
    0.42
     ፡፡
    0.35
    ۔
    0.35
    །
    0.34
    ።
    0.32
    。
    0.31
    သည်။
    0.31
    ’।
    0.31
    |।
    0.30
    ။
    0.30
    Act Density 0.046%

    No Known Activations