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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pagan
    -0.07
     GetData
    -0.06
     numer
    -0.06
     handic
    -0.06
     far
    -0.06
     qual
    -0.06
     Tree
    -0.06
     corrobor
    -0.05
     "\
    -0.05
     Hands
    -0.05
    POSITIVE LOGITS
    
    0.07
    -spinner
    0.06
     cinematic
    0.06
     wreak
    0.06
    fighter
    0.06
    국의
    0.06
    _JOB
    0.06
     investments
    0.06
    ้องน
    0.06
    mm
    0.06
    Act Density 0.102%

    No Known Activations