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

    Neuronpedia

    INDEX
    Explanations

    justifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Batman
    -0.07
    Э
    -0.07
    Chem
    -0.07
    资
    -0.06
     COPYING
    -0.06
     lowercase
    -0.06
    された
    -0.06
     созда
    -0.06
     countryside
    -0.06
     maxLength
    -0.06
    POSITIVE LOGITS
    den
    0.06
    imir
    0.06
    ΥΣ
    0.06
     手
    0.06
    hlen
    0.06
     BJP
    0.06
    alez
    0.06
     pct
    0.06
    irs
    0.06
     EIF
    0.06
    Act Density 0.041%

    No Known Activations