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

    Neuronpedia

    INDEX
    Explanations

    medical/technical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linspace
    -0.07
    past
    -0.07
     liking
    -0.07
     regular
    -0.06
    -bordered
    -0.06
    .collider
    -0.06
     orally
    -0.06
     volt
    -0.06
    ający
    -0.06
    꿏
    -0.06
    POSITIVE LOGITS
    mith
    0.07
     Leigh
    0.07
    前夕
    0.07
    זכר
    0.07
     Automotive
    0.07
    _LIB
    0.07
    .set
    0.06
    brtc
    0.06
     Teen
    0.06
    牵
    0.06
    Act Density 0.227%

    No Known Activations