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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仔
    -0.07
    💜
    -0.07
    .proj
    -0.07
    仝
    -0.07
    .endswith
    -0.07
    苣
    -0.06
     teaches
    -0.06
    /J
    -0.06
    檬
    -0.06
    洋葱
    -0.06
    POSITIVE LOGITS
    _PLATFORM
    0.07
    切实
    0.07
     WAV
    0.06
     Movement
    0.06
    偡
    0.06
    _COORD
    0.06
     Lesser
    0.06
    实施方案
    0.06
     święt
    0.06
     customization
    0.06
    Act Density 0.002%

    No Known Activations