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

    Neuronpedia

    INDEX
    Explanations

    theater

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pNode
    -0.07
     Event
    -0.07
     spin
    -0.06
    -transform
    -0.06
    ,title
    -0.06
     Sentry
    -0.06
     mojo
    -0.06
    ullah
    -0.06
     Astronomy
    -0.06
     Cloth
    -0.06
    POSITIVE LOGITS
    Honda
    0.07
    -educated
    0.07
    　　
    0.07
    Allocate
    0.06
    Son
    0.06
    内
    0.06
    Increased
    0.06
    spir
    0.06
    memory
    0.06
    Supply
    0.06
    Act Density 0.015%

    No Known Activations