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

    Neuronpedia

    INDEX
    Explanations

    online discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mathematics
    -0.07
     Gentle
    -0.07
     jelly
    -0.07
     dy
    -0.06
    graduate
    -0.06
    EMPLARY
    -0.06
    /dis
    -0.06
    -negative
    -0.06
    _DIS
    -0.06
    伦理
    -0.06
    POSITIVE LOGITS
    'être
    0.08
    확
    0.08
    好转
    0.07
     xếp
    0.07
    愎
    0.07
    .exit
    0.07
    왜
    0.07
    遷
    0.07
    (".");↵
    0.07
     replacements
    0.07
    Act Density 0.036%

    No Known Activations