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

    Neuronpedia

    INDEX
    Explanations

    verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulum
    -0.09
    Raw
    -0.07
     Employee
    -0.06
    -options
    -0.06
     Running
    -0.06
    -स
    -0.06
     continuing
    -0.06
    ferences
    -0.06
    ---------
    -0.06
     rằng
    -0.06
    POSITIVE LOGITS
    inging
    0.07
    '})↵↵
    0.06
    во
    0.06
    Controls
    0.06
    เค
    0.06
     credited
    0.06
    ".$_
    0.06
    inged
    0.06
     Acquisition
    0.06
     количество
    0.06
    Act Density 0.067%

    No Known Activations