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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    シ
    -0.07
    _gap
    -0.06
     ery
    -0.06
     Hond
    -0.06
     ri
    -0.06
    RF
    -0.06
    скую
    -0.06
     čím
    -0.06
     lev
    -0.06
     CSI
    -0.06
    POSITIVE LOGITS
     Contents
    0.06
     Memo
    0.06
     mesmer
    0.06
     bootloader
    0.06
     '''
↵
    0.06
    _letters
    0.06
    �
    0.06
     choix
    0.06
     communic
    0.06
     Nous
    0.06
    Act Density 0.062%

    No Known Activations