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

    Neuronpedia

    INDEX
    Explanations

    Code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PPP
    -0.07
    HEME
    -0.07
    .partner
    -0.07
    '")↵
    -0.06
    ولد
    -0.06
    리의
    -0.06
    [dir
    -0.06
     absol
    -0.06
    loads
    -0.06
    Faces
    -0.06
    POSITIVE LOGITS
    ＿＿
    0.06
     бли
    0.06
    -story
    0.06
    -depth
    0.06
     schle
    0.06
    075
    0.06
    -online
    0.06
     coarse
    0.06
     суд
    0.06
    .TIM
    0.06
    Act Density 3.144%

    No Known Activations