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

    Neuronpedia

    INDEX
    Explanations

    say "'s"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .bpm
    -0.07
    unnel
    -0.07
    522
    -0.06
    CAP
    -0.06
    );;↵
    -0.06
     programas
    -0.06
    Act
    -0.06
    produce
    -0.06
    -ahead
    -0.06
    üh
    -0.06
    POSITIVE LOGITS
     students
    0.06
     �
    0.06
     dưới
    0.06
    άβ
    0.06
    UniformLocation
    0.06
     تقویت
    0.06
     Augustine
    0.06
     війсь
    0.06
     اسلام
    0.06
    реж
    0.06
    Act Density 0.017%

    No Known Activations