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

    Neuronpedia

    INDEX
    Explanations

    News articles with dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     barg
    -0.07
    Mgr
    -0.07
    _ma
    -0.07
     Fred
    -0.07
    ,new
    -0.06
    mercial
    -0.06
    win
    -0.06
    ceed
    -0.06
    -search
    -0.06
    ny
    -0.06
    POSITIVE LOGITS
    464
    0.07
     EDT
    0.06
     которой
    0.06
    850
    0.06
    JUnit
    0.06
     складу
    0.06
    .inflate
    0.06
    .alias
    0.06
     kcal
    0.06
     لباس
    0.06
    Act Density 0.437%

    No Known Activations