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

    Neuronpedia

    INDEX
    Explanations

    Contrasting two concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    шив
    -0.07
     *
↵
    -0.07
    ísto
    -0.07
    τού
    -0.07
     Suites
    -0.06
    Gui
    -0.06
     Chef
    -0.06
    leting
    -0.06
    >"↵
    -0.06
     )
↵
    -0.06
    POSITIVE LOGITS
     Dragon
    0.06
    	Resource
    0.06
    Beauty
    0.06
     Iss
    0.06
    cx
    0.06
    'action
    0.06
     Turkish
    0.06
    .keyboard
    0.06
     SYSTEM
    0.06
     brightest
    0.05
    Act Density 0.019%

    No Known Activations