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

    Neuronpedia

    INDEX
    Explanations

    Standard SQL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    딯
    -0.09
    所需
    -0.07
    ('"
    -0.07
     Termin
    -0.07
    เทคโนโล
    -0.06
     Limits
    -0.06
    etros
    -0.06
    ",__
    -0.06
     chặ
    -0.06
     feminist
    -0.06
    POSITIVE LOGITS
    탑
    0.07
     Hydra
    0.07
    slider
    0.07
     miner
    0.07
    modify
    0.07
     expedition
    0.07
    UB
    0.07
    quivos
    0.06
    	y
    0.06
     occupants
    0.06
    Act Density 0.030%

    No Known Activations