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

    Neuronpedia

    INDEX
    Explanations

    with/has

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     صف
    -0.07
    _ext
    -0.07
     عب
    -0.07
    цип
    -0.06
    wrapper
    -0.06
    fullname
    -0.06
     чис
    -0.06
     corridor
    -0.06
    (counter
    -0.06
     bee
    -0.06
    POSITIVE LOGITS
    	ok
    0.07
    �
    0.07
     vej
    0.06
     skulle
    0.06
    GIT
    0.06
    -',
    0.06
    .CL
    0.06
    opped
    0.06
    ุง
    0.06
    .old
    0.06
    Act Density 0.019%

    No Known Activations