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

    Neuronpedia

    INDEX
    Explanations

    Non-english text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     optimized
    -0.06
     associate
    -0.06
    ош
    -0.06
     exploded
    -0.06
    plement
    -0.06
     fiction
    -0.06
    .reference
    -0.06
     please
    -0.06
     سو
    -0.06
     challenges
    -0.06
    POSITIVE LOGITS
     Jill
    0.07
     tutto
    0.07
    (integer
    0.06
     mamma
    0.06
    ندگی
    0.06
     tomto
    0.06
     неиз
    0.06
     ><?
    0.06
    ，便
    0.06
    ?action
    0.06
    Act Density 0.041%

    No Known Activations