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

    Neuronpedia

    INDEX
    Explanations

    night

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yana
    -0.06
     схем
    -0.06
     gezocht
    -0.06
     місто
    -0.06
    isay
    -0.06
    ASON
    -0.06
    iqué
    -0.06
    AAC
    -0.05
    ModelCreating
    -0.05
    ).__
    -0.05
    POSITIVE LOGITS
     itu
    0.07
    ρός
    0.07
    .scalar
    0.07
     aid
    0.07
    이를
    0.06
    ension
    0.06
    .set
    0.06
     dangers
    0.06
    -notification
    0.06
     uncertainty
    0.06
    Act Density 0.300%

    No Known Activations