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

    Neuronpedia

    INDEX
    Explanations

    programming, technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     міс
    -0.07
     робот
    -0.07
     angrily
    -0.07
    Anal
    -0.07
     گوشی
    -0.06
     MPU
    -0.06
    خف
    -0.06
     найбіль
    -0.06
     بزرگ
    -0.06
     incontri
    -0.06
    POSITIVE LOGITS
    .amazon
    0.07
    raft
    0.06
     memoir
    0.06
     purpose
    0.06
    animals
    0.06
    /testing
    0.06
    _environment
    0.06
    eward
    0.06
    Bundle
    0.06
    _guide
    0.06
    Act Density 0.180%

    No Known Activations