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

    Neuronpedia

    INDEX
    Explanations

    Legal/sales terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outward
    -0.07
     sociale
    -0.06
     folks
    -0.06
     тру
    -0.06
     Lar
    -0.06
    ظة
    -0.06
     evils
    -0.06
    gren
    -0.06
    ildo
    -0.06
     и
    -0.06
    POSITIVE LOGITS
    (minutes
    0.07
     Siber
    0.06
     phoenix
    0.06
    delivr
    0.06
    -order
    0.06
    REAT
    0.06
     injecting
    0.06
    Written
    0.06
    _abstract
    0.06
    اضر
    0.06
    Act Density 0.005%

    No Known Activations