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

    Neuronpedia

    INDEX
    Explanations

    draw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inauguration
    -0.07
    ула
    -0.07
     embry
    -0.07
    clarations
    -0.07
    urma
    -0.07
    bursement
    -0.07
     mezun
    -0.07
    leet
    -0.06
     кла
    -0.06
     toler
    -0.06
    POSITIVE LOGITS
    MODULE
    0.06
    tip
    0.06
    _skills
    0.06
     man
    0.06
     swirling
    0.06
    -handle
    0.06
     getSupportFragmentManager
    0.06
     firefighters
    0.06
    .qq
    0.06
     naopak
    0.06
    Act Density 0.004%

    No Known Activations