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

    Neuronpedia

    INDEX
    Explanations

    *

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    perial
    -0.07
    forget
    -0.07
     despair
    -0.07
     weddings
    -0.07
     roaring
    -0.07
     camps
    -0.06
    jištění
    -0.06
     된다
    -0.06
     awe
    -0.06
    광고
    -0.06
    POSITIVE LOGITS
     dB
    0.07
     fulfill
    0.07
    ertz
    0.06
    turnstile
    0.06
    PR
    0.06
     Mods
    0.06
     Errors
    0.06
    aniel
    0.06
     contentious
    0.06
     mods
    0.06
    Act Density 0.000%

    No Known Activations