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

    Neuronpedia

    INDEX
    Explanations

    hardness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mejores
    -0.07
    nač
    -0.07
     Asset
    -0.07
     زی
    -0.06
     qualifications
    -0.06
     elem
    -0.06
     Coord
    -0.06
     bile
    -0.06
     pd
    -0.06
    析
    -0.06
    POSITIVE LOGITS
     hardness
    0.08
    uridad
    0.07
    toi
    0.07
    (resource
    0.07
    ufs
    0.07
    ości
    0.06
    terior
    0.06
    (manager
    0.06
    lev
    0.06
    .fromCharCode
    0.06
    Act Density 0.003%

    No Known Activations