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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gel
    -0.07
    购车
    -0.07
    _lit
    -0.07
     Liz
    -0.07
     Granted
    -0.06
     leopard
    -0.06
     dilemma
    -0.06
     chin
    -0.06
    🦀
    -0.06
     plur
    -0.06
    POSITIVE LOGITS
    _neurons
    0.07
    𬕂
    0.07
    \":{\"
    0.07
     standoff
    0.06
     fft
    0.06
    _armor
    0.06
     Detect
    0.06
     SENSOR
    0.06
     sprites
    0.06
    .direction
    0.06
    Act Density 0.012%

    No Known Activations