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

    Neuronpedia

    INDEX
    Explanations

    в

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expert
    -0.07
     VAL
    -0.06
    Near
    -0.06
     incurred
    -0.06
     Dur
    -0.06
    逆
    -0.06
     delicate
    -0.06
     vulgar
    -0.06
    ельзя
    -0.06
     estava
    -0.06
    POSITIVE LOGITS
    だって
    0.07
    لیه
    0.07
    _platform
    0.07
    opher
    0.07
    _else
    0.06
    -unit
    0.06
    pizza
    0.06
    送料
    0.06
    GameObject
    0.06
    ž
    0.06
    Act Density 0.206%

    No Known Activations