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

    Neuronpedia

    INDEX
    Explanations

    It

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UEST
    -0.07
    ✟
    -0.07
    ],"
    -0.06
    <Course
    -0.06
    Fuse
    -0.06
    Jess
    -0.06
    ҫ
    -0.06
    OKEN
    -0.06
    }</
    -0.06
    !</
    -0.06
    POSITIVE LOGITS
     الحديد
    0.07
     Finger
    0.07
     Scheduled
    0.07
    سكن
    0.07
    参照
    0.07
    新的一
    0.07
    啪
    0.07
     Restrictions
    0.07
     flashlight
    0.07
     prosper
    0.07
    Act Density 0.244%

    No Known Activations