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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lian
    -0.07
    _serv
    -0.07
     textbox
    -0.07
     Features
    -0.06
     biography
    -0.06
    \Tests
    -0.06
     نوشته
    -0.06
     Explanation
    -0.06
    _HEAP
    -0.06
    Newsletter
    -0.06
    POSITIVE LOGITS
    lz
    0.06
    568
    0.06
    …the
    0.06
    __,__
    0.06
    zing
    0.06
    ъек
    0.06
     Romania
    0.06
     Dropbox
    0.06
    OR
    0.06
     popover
    0.06
    Act Density 0.032%

    No Known Activations