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

    Neuronpedia

    INDEX
    Explanations

    language puzzles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SUBJECT
    -0.08
    Tab
    -0.08
    Pressure
    -0.07
    .Month
    -0.07
    ,new
    -0.07
     Với
    -0.07
    upp
    -0.06
    _MODEL
    -0.06
     هش
    -0.06
    亮
    -0.06
    POSITIVE LOGITS
     bicy
    0.06
     Compiled
    0.06
    servers
    0.06
     guts
    0.06
     reclaim
    0.06
     электр
    0.06
     مغ
    0.06
    mos
    0.05
     этим
    0.05
     рес
    0.05
    Act Density 0.041%

    No Known Activations