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

    Neuronpedia

    INDEX
    Explanations

    BL

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drink
    -0.06
     Hiro
    -0.06
    Za
    -0.06
     exter
    -0.06
    '#
    -0.06
    ometr
    -0.06
     mai
    -0.06
     chron
    -0.06
    idan
    -0.06
     Henry
    -0.06
    POSITIVE LOGITS
     horsepower
    0.07
     keyCode
    0.06
    |RF
    0.06
     potassium
    0.06
    spd
    0.06
     انگلیسی
    0.06
     attribution
    0.06
    ]
↵
    0.06
    ové
    0.06
     motivation
    0.06
    Act Density 0.012%

    No Known Activations