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

    Neuronpedia

    INDEX
    Explanations

    Gaining or denying access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERVE
    -0.07
    벤
    -0.06
     fiance
    -0.06
     tilt
    -0.06
     fax
    -0.06
     K
    -0.06
    紹
    -0.06
    итися
    -0.06
     push
    -0.06
    arded
    -0.06
    POSITIVE LOGITS
     [`
    0.07
    .isActive
    0.07
    mac
    0.07
    clazz
    0.06
    Bindable
    0.06
    (DIS
    0.06
     origen
    0.06
    agenda
    0.06
    ुझ
    0.06
     вспом
    0.06
    Act Density 0.023%

    No Known Activations