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

    Neuronpedia

    INDEX
    Explanations

    People

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     graduation
    -0.06
    Qualified
    -0.06
     kan
    -0.06
     Define
    -0.06
    omething
    -0.06
     large
    -0.06
     yüzyıl
    -0.06
    /reference
    -0.06
    _Method
    -0.06
     годы
    -0.06
    POSITIVE LOGITS
     Abd
    0.06
    forms
    0.06
    ;$
    0.06
     Glock
    0.06
    	spin
    0.06
     thanking
    0.06
     biting
    0.06
    	df
    0.06
    fab
    0.06
    .bridge
    0.06
    Act Density 0.057%

    No Known Activations