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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Phone
    -0.06
     You
    -0.06
     мереж
    -0.06
    -percent
    -0.06
    Agregar
    -0.06
     vetor
    -0.06
     Symptoms
    -0.06
     sh
    -0.06
    _tmp
    -0.06
     وهي
    -0.06
    POSITIVE LOGITS
     righteous
    0.07
    614
    0.07
     Clara
    0.07
    usual
    0.07
    IndexPath
    0.06
    (LocalDate
    0.06
    incr
    0.06
    切
    0.06
    ヾ
    0.06
     Christoph
    0.06
    Act Density 0.011%

    No Known Activations