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

    Neuronpedia

    INDEX
    Explanations

    eters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “No
    -0.07
    (Convert
    -0.07
     cathedral
    -0.06
     ProgressBar
    -0.06
     Ware
    -0.06
     avocado
    -0.06
     press
    -0.06
     середови
    -0.06
     Healing
    -0.06
    .Edit
    -0.06
    POSITIVE LOGITS
    arium
    0.07
     JPEG
    0.06
    别
    0.06
    .txt
    0.06
    ДК
    0.06
    باب
    0.06
    .multi
    0.06
    kı
    0.06
    buster
    0.06
     м
    0.06
    Act Density 0.446%

    No Known Activations