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

    Neuronpedia

    INDEX
    Explanations

    Seeing where it leads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implants
    -0.08
     extensions
    -0.07
    ulty
    -0.07
    riz
    -0.07
     stuff
    -0.06
    akis
    -0.06
    ’re
    -0.06
    Tuple
    -0.06
    d
    -0.06
     distribution
    -0.06
    POSITIVE LOGITS
    ='../
    0.06
     messing
    0.06
    .ingredients
    0.06
    =format
    0.06
    PTS
    0.06
    .enemy
    0.06
    .ST
    0.06
     Pan
    0.06
     บาง
    0.06
    (ast
    0.06
    Act Density 0.020%

    No Known Activations