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

    Neuronpedia

    INDEX
    Explanations

    Listing possibilities/reasons/examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unsus
    -0.07
     technology
    -0.07
    (bl
    -0.07
    ighth
    -0.07
    ru
    -0.06
     spouse
    -0.06
     nichž
    -0.06
     ______
    -0.06
     її
    -0.06
     budget
    -0.06
    POSITIVE LOGITS
    練
    0.07
    ेण
    0.06
    verbose
    0.06
     DateFormatter
    0.06
     chce
    0.06
     cameo
    0.06
    _PD
    0.06
    encial
    0.06
    WithTag
    0.06
    ENTIAL
    0.05
    Act Density 0.053%

    No Known Activations