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

    Neuronpedia

    INDEX
    Explanations

    code and server configurations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	debug
    -0.08
     dent
    -0.07
    entity
    -0.07
    να
    -0.07
     loyal
    -0.07
    	fields
    -0.07
     Vill
    -0.06
     agreed
    -0.06
     sdk
    -0.06
    	func
    -0.06
    POSITIVE LOGITS
     audition
    0.08
    eydi
    0.07
    _playlist
    0.07
    externalActionCode
    0.06
    ai
    0.06
    sphere
    0.06
    ionate
    0.06
     vỏ
    0.06
     pageTitle
    0.06
    laşma
    0.06
    Act Density 0.022%

    No Known Activations