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

    Neuronpedia

    INDEX
    Explanations

    orphan boy, alien insects, Junk Shop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒊑
    1.91
    𒈪
    1.90
     parametros
    1.86
    𒊓
    1.84
    ̀ng
    1.84
    𒌷
    1.84
    𒅕
    1.84
    ቝ
    1.83
    𒌵
    1.82
    𒐊
    1.82
    POSITIVE LOGITS
     (
    1.26
     chief
    1.22
     that
    1.21
    ,
    1.17
     name
    1.14
     on
    1.12
     story
    1.11
     and
    1.10
     is
    1.09
     apparently
    1.07
    Act Density 0.283%

    No Known Activations