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

    Neuronpedia

    INDEX
    Explanations

    than, the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    angstrom
    -0.08
     NPCs
    -0.08
     chicago
    -0.07
    пись
    -0.07
     BMW
    -0.07
     Jacksonville
    -0.07
    米饭
    -0.07
     Plot
    -0.07
    帳號
    -0.07
    𝓋
    -0.07
    POSITIVE LOGITS
    _em
    0.07
    clear
    0.07
    ’é
    0.07
     Includes
    0.07
     المؤتمر
    0.07
     destination
    0.07
    当作
    0.07
    等工作
    0.07
    -used
    0.07
     preceding
    0.06
    Act Density 0.001%

    No Known Activations