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

    Neuronpedia

    INDEX
    Explanations

    maximize equations with variables

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ван
    -0.07
     risc
    -0.07
    heds
    -0.07
    Drivers
    -0.07
     patiently
    -0.07
    Luck
    -0.07
     liquidation
    -0.07
     Lia
    -0.07
     weten
    -0.07
    гу
    -0.07
    POSITIVE LOGITS
     cláss
    0.08
     surat
    0.08
    染
    0.08
    �
    0.08
    resents
    0.08
     Surveys
    0.07
    鱼
    0.07
     Retina
    0.07
     EMA
    0.07
     παρουσιά
    0.07
    Act Density 0.008%

    No Known Activations