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

    Neuronpedia

    INDEX
    Explanations

    pahunch, pahadon, Pahang

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JEN
    0.42
     Dallas
    0.41
     স্বদেশ
    0.38
     środ
    0.38
     Doherty
    0.38
     FE
    0.38
     Meille
    0.37
    Dallas
    0.37
     founded
    0.37
     GRI
    0.37
    POSITIVE LOGITS
     pah
    0.47
     algorithmic
    0.45
    lej
    0.42
     algorit
    0.41
     compositional
    0.41
     უფ
    0.40
    algam
    0.40
    algorithmic
    0.39
    լ
    0.39
    loot
    0.38
    Act Density 0.000%

    No Known Activations