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

    Neuronpedia

    INDEX
    Explanations

    distinct words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insanların
    0.47
    topnav
    0.47
    𝘬
    0.47
    loadConst
    0.46
    ری
    0.46
    pretrained
    0.45
    airo
    0.44
    Vertices
    0.44
    ﻙ
    0.44
    cog
    0.44
    POSITIVE LOGITS
    em
    0.47
    ,
    0.46
    en
    0.45
     interests
    0.44
     lemma
    0.42
     lower
    0.41
    ropy
    0.41
    ités
    0.41
    andez
    0.39
     proposal
    0.39
    Act Density 0.005%

    No Known Activations