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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _LENGTH
    -0.07
     sincerity
    -0.07
    (snapshot
    -0.07
    avour
    -0.07
    -gallery
    -0.06
     он
    -0.06
     gz
    -0.06
    070
    -0.06
    493
    -0.06
    ADIUS
    -0.06
    POSITIVE LOGITS
     CLAIM
    0.07
     jednotlivých
    0.07
     wreak
    0.06
     研
    0.06
     heck
    0.06
     cite
    0.06
     наб
    0.06
    êt
    0.06
    .RequestParam
    0.06
    -fed
    0.06
    Act Density 0.001%

    No Known Activations