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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ช่วย
    -0.08
     meanwhile
    -0.08
     Nano
    -0.08
    Interop
    -0.08
     incorporating
    -0.07
    ועל
    -0.07
    ಳ್ಳ
    -0.07
     يعمل
    -0.07
     depleted
    -0.07
     hoạt
    -0.07
    POSITIVE LOGITS
    orab
    0.08
     কে
    0.08
     এল
    0.08
    alb
    0.08
    距
    0.07
     confusing
    0.07
     textbook
    0.07
    கு
    0.07
     Alison
    0.07
     отличный
    0.07
    Act Density 0.072%

    No Known Activations