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

    Neuronpedia

    INDEX
    Explanations

    Legal citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Real
    -0.07
     bure
    -0.06
    Current
    -0.06
     benzer
    -0.06
    _W
    -0.06
     reported
    -0.06
     -$
    -0.05
    _legend
    -0.05
    ipes
    -0.05
    /th
    -0.05
    POSITIVE LOGITS
     واحد
    0.07
    Definitions
    0.07
     방법
    0.07
     müda
    0.07
     unfold
    0.06
    auf
    0.06
    .Mouse
    0.06
     Programme
    0.06
     salle
    0.06
     نام
    0.06
    Act Density 0.001%

    No Known Activations