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

    Neuronpedia

    INDEX
    Explanations

    code fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     easy
    -0.07
     Sang
    -0.07
    _neg
    -0.07
    -gnu
    -0.07
    .Reflection
    -0.07
    easy
    -0.07
    -east
    -0.06
    Filtered
    -0.06
     Hour
    -0.06
    ,opt
    -0.06
    POSITIVE LOGITS
    ísk
    0.06
    že
    0.06
    resent
    0.06
     replica
    0.06
    ptune
    0.06
     imp
    0.06
     رفتار
    0.06
    endencies
    0.06
     rupture
    0.06
    taire
    0.06
    Act Density 0.000%

    No Known Activations