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

    Neuronpedia

    INDEX
    Explanations

    Code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Morris
    -0.07
    ことは
    -0.07
     checksum
    -0.07
     preval
    -0.07
     רש
    -0.06
    elm
    -0.06
    _Register
    -0.06
    ibur
    -0.06
    畢竟
    -0.06
    쉼
    -0.06
    POSITIVE LOGITS
    向往
    0.08
     getLocation
    0.07
    .SECONDS
    0.07
    Creat
    0.07
     myst
    0.07
    .va
    0.07
     noisy
    0.07
     PHYS
    0.07
     أثناء
    0.07
     Pentagon
    0.07
    Act Density 0.021%

    No Known Activations