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

    Neuronpedia

    INDEX
    Explanations

    GROUP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Atkins
    -0.07
     Myers
    -0.07
    friends
    -0.07
     barrier
    -0.06
     Falk
    -0.06
     Lebens
    -0.06
     Vũ
    -0.06
     worldwide
    -0.06
    _notice
    -0.06
     박
    -0.06
    POSITIVE LOGITS
    iná
    0.07
    Feel
    0.07
    IEWS
    0.06
     assorted
    0.06
     Magento
    0.06
    Cross
    0.06
     convertible
    0.06
    ensi
    0.06
     pornos
    0.05
    elu
    0.05
    Act Density 0.012%

    No Known Activations