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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plate
    -0.08
    พระ
    -0.07
    .logout
    -0.07
     Watches
    -0.07
     liberalism
    -0.07
     plates
    -0.07
     initialised
    -0.07
     good
    -0.07
     WhatsApp
    -0.06
     lei
    -0.06
    POSITIVE LOGITS
     [["
    0.06
    ＼
    0.06
     joked
    0.06
     โดย
    0.06
    (delta
    0.06
    éo
    0.06
     남자
    0.06
    еком
    0.06
    PCM
    0.06
    ConstraintMaker
    0.06
    Act Density 0.396%

    No Known Activations