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

    Neuronpedia

    INDEX
    Explanations

    Brackets and colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vu
    -0.06
    .ham
    -0.06
    _pw
    -0.06
    jím
    -0.06
     retina
    -0.06
    вих
    -0.06
     mất
    -0.06
    Mary
    -0.06
    root
    -0.06
    째
    -0.06
    POSITIVE LOGITS
     Lockheed
    0.07
    _NON
    0.07
     алког
    0.06
     chronic
    0.06
     padded
    0.06
     即
    0.06
    IBOutlet
    0.06
     Financing
    0.06
    ....
    0.06
     rectangular
    0.06
    Act Density 0.011%

    No Known Activations