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

    Neuronpedia

    INDEX
    Explanations

    say "infrared"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quiring
    -0.07
    Composer
    -0.07
     UPDATE
    -0.07
    essional
    -0.06
    影响
    -0.06
    Ant
    -0.06
     Actor
    -0.06
    事
    -0.06
    alist
    -0.06
     Rental
    -0.06
    POSITIVE LOGITS
     Netanyahu
    0.08
     Cyr
    0.07
    _bel
    0.06
     Unc
    0.06
    ослав
    0.06
    _examples
    0.06
     �
    0.06
    .addProperty
    0.06
    _most
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations