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

    Neuronpedia

    INDEX
    Explanations

    Cent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unlocked
    -0.06
     Dal
    -0.06
     subsystem
    -0.06
    hdl
    -0.06
    readOnly
    -0.06
    FDA
    -0.06
     madness
    -0.06
     tid
    -0.06
     halves
    -0.06
     动
    -0.06
    POSITIVE LOGITS
    िरफ
    0.08
    writes
    0.07
    &P
    0.07
     chrono
    0.07
     Bengals
    0.06
     شرح
    0.06
    بار
    0.06
    erusform
    0.06
     лим
    0.06
    ,count
    0.06
    Act Density 0.002%

    No Known Activations