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

    Neuronpedia

    INDEX
    Explanations

    aspects and characteristics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ).
    0.43
    调度
    0.43
    and
    0.43
     prayer
    0.43
    रण
    0.42
    Lod
    0.41
    Brun
    0.41
    \...
    0.40
    溜
    0.40
    ?
    0.40
    POSITIVE LOGITS
     되었다
    0.52
     enanti
    0.51
     reunite
    0.51
     formes
    0.50
     macromolecules
    0.50
    ದಲ
    0.50
     Bhosle
    0.50
     CMake
    0.50
     rashes
    0.49
     venne
    0.49
    Act Density 0.009%

    No Known Activations