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

    Neuronpedia

    INDEX
    Explanations

    Support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    旦
    -0.07
    SGlobal
    -0.07
    III
    -0.07
    II
    -0.07
    (File
    -0.06
     Sharia
    -0.06
    느
    -0.06
    νη
    -0.06
    :X
    -0.06
    液
    -0.06
    POSITIVE LOGITS
    Support
    0.07
     technician
    0.06
     действия
    0.06
    iffany
    0.06
    ?)↵↵
    0.06
     Perform
    0.06
    ่าเป
    0.06
    ส
    0.06
     Лу
    0.06
    û
    0.06
    Act Density 0.000%

    No Known Activations