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

    Neuronpedia

    INDEX
    Explanations

    rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Dust
    -0.07
     particles
    -0.07
     entwick
    -0.06
     pero
    -0.06
    еро
    -0.06
     PARTIC
    -0.06
     inquiries
    -0.06
     فی
    -0.06
     probe
    -0.06
    POSITIVE LOGITS
     squared
    0.06
    -port
    0.06
    blems
    0.06
    -choice
    0.06
    School
    0.06
     murderer
    0.06
     subtle
    0.06
     "}
    0.06
    datal
    0.06
     있어서
    0.06
    Act Density 0.003%

    No Known Activations