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

    Neuronpedia

    INDEX
    Explanations

    dimensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vener
    -0.07
     Ferr
    -0.07
     loan
    -0.06
    mma
    -0.06
     данны
    -0.06
     hesitation
    -0.06
     tenure
    -0.06
     бук
    -0.06
     fas
    -0.06
     lift
    -0.06
    POSITIVE LOGITS
    ्शन
    0.07
    -setup
    0.07
     handleMessage
    0.07
    .GetEnumerator
    0.07
     ><
    0.06
     bởi
    0.06
    sky
    0.06
     Fixes
    0.06
    Translate
    0.06
    oux
    0.06
    Act Density 0.009%

    No Known Activations