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

    Neuronpedia

    INDEX
    Explanations

    radiator

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    εις
    -0.06
    alarını
    -0.06
    .userName
    -0.06
    uppen
    -0.06
    (destination
    -0.06
     ejemplo
    -0.06
     atas
    -0.06
     impunity
    -0.06
    keterangan
    -0.06
     Skywalker
    -0.06
    POSITIVE LOGITS
     radiator
    0.10
    Message
    0.07
     dri
    0.07
     rigid
    0.07
     KIND
    0.07
     matrix
    0.06
    Liquid
    0.06
     Sail
    0.06
    ри
    0.06
    是在
    0.06
    Act Density 0.001%

    No Known Activations