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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Regulatory
    -0.06
     Miz
    -0.06
     acute
    -0.06
     �
    -0.06
     Pool
    -0.06
    	word
    -0.06
     pesticide
    -0.06
     PIX
    -0.06
     Square
    -0.06
     बस
    -0.06
    POSITIVE LOGITS
     xmlDoc
    0.07
    their
    0.07
    levard
    0.06
    _regularizer
    0.06
     líder
    0.06
    Mage
    0.06
    ійного
    0.06
    >("
    0.06
    FetchRequest
    0.06
     sessuali
    0.06
    Act Density 0.078%

    No Known Activations