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

    Neuronpedia

    INDEX
    Explanations

    necessarily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fluor
    -0.07
     Stout
    -0.07
    лор
    -0.07
    查询
    -0.07
    經
    -0.07
    _stat
    -0.07
     genome
    -0.06
    ROT
    -0.06
    Recently
    -0.06
     recently
    -0.06
    POSITIVE LOGITS
     necessarily
    0.09
    後の
    0.07
    !
↵
    0.07
     выращи
    0.07
     Dependencies
    0.07
     связ
    0.07
     
↵
    0.07
     служ
    0.07
    metrical
    0.06
     olduk
    0.06
    Act Density 0.009%

    No Known Activations