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

    Neuronpedia

    INDEX
    Explanations

    _State

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     insistence
    -0.07
     kendi
    -0.07
     ettiği
    -0.06
     knives
    -0.06
    킨
    -0.06
     doubts
    -0.06
    じゃない
    -0.06
     СП
    -0.06
    luent
    -0.06
     unserer
    -0.06
    POSITIVE LOGITS
     organising
    0.07
     Dram
    0.07
     Dies
    0.06
    官网
    0.06
     Anim
    0.06
     BOT
    0.06
     Consum
    0.06
     VERBOSE
    0.06
    (`↵
    0.06
    [tid
    0.06
    Act Density 0.002%

    No Known Activations