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

    Neuronpedia

    INDEX
    Explanations

    but or comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Command
    -0.06
    _request
    -0.06
    (user
    -0.06
    ании
    -0.06
    462
    -0.06
    _prob
    -0.06
     Cable
    -0.06
     reusable
    -0.06
    422
    -0.06
    602
    -0.06
    POSITIVE LOGITS
     Başkan
    0.07
    anggan
    0.07
    _published
    0.06
    /functions
    0.06
    Sad
    0.06
     '$
    0.06
     hey
    0.06
     прим
    0.06
     did
    0.06
     muslim
    0.06
    Act Density 0.018%

    No Known Activations