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

    Neuronpedia

    INDEX
    Explanations

    all, every, situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fluvial
    0.50
     tain
    0.48
     such
    0.46
     smuggling
    0.46
     parametrization
    0.45
     vanishes
    0.44
     quenching
    0.44
     suche
    0.43
     gist
    0.43
     discoloration
    0.43
    POSITIVE LOGITS
     всех
    0.48
    все
    0.47
    ждый
    0.47
    将在
    0.46
    艺术家
    0.45
     всеми
    0.43
    放弃
    0.43
     Sprache
    0.43
     όλ
    0.43
    我和
    0.43
    Act Density 0.003%

    No Known Activations