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

    Neuronpedia

    INDEX
    Explanations

    avatar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _instruction
    -0.08
    .Warning
    -0.07
     explosives
    -0.07
    istrator
    -0.07
     getIndex
    -0.07
     Compound
    -0.07
    Compound
    -0.07
     impose
    -0.06
     melanch
    -0.06
     bonds
    -0.06
    POSITIVE LOGITS
     av
    0.07
    нути
    0.07
    eras
    0.06
    av
    0.06
    лов
    0.06
    віт
    0.06
    ΑΤ
    0.06
     خبر
    0.06
    ает
    0.06
    ا�
    0.06
    Act Density 0.002%

    No Known Activations