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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ař
    -0.08
    igos
    -0.07
    _para
    -0.06
    ترل
    -0.06
    ประส
    -0.06
    еної
    -0.06
     Ад
    -0.06
    .Listen
    -0.06
    actually
    -0.06
    исс
    -0.06
    POSITIVE LOGITS
    (inplace
    0.07
     avocado
    0.07
    侍
    0.06
    orrar
    0.06
    ArrayType
    0.06
     tutors
    0.06
     золот
    0.06
     manner
    0.06
    �
    0.06
    sortBy
    0.06
    Act Density 0.001%

    No Known Activations