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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cookies
    -0.07
    look
    -0.06
    -specific
    -0.06
    ὶ
    -0.06
    اض
    -0.06
     clumsy
    -0.06
    ウス
    -0.06
     preferably
    -0.06
     dyn
    -0.06
    _reference
    -0.06
    POSITIVE LOGITS
     noss
    0.06
    (CONFIG
    0.06
    Superview
    0.06
    _inventory
    0.06
    sınız
    0.06
     gore
    0.06
    (KEY
    0.06
     {...
    0.06
    	sn
    0.06
    (Session
    0.06
    Act Density 0.057%

    No Known Activations