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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _tar
    -0.08
    /page
    -0.08
     media
    -0.07
     fly
    -0.07
     alloy
    -0.07
     Otto
    -0.07
    Late
    -0.07
    Archivo
    -0.07
     вер
    -0.07
    意味着
    -0.06
    POSITIVE LOGITS
    教育教学
    0.07
    ACS
    0.07
     Андр
    0.07
     unseren
    0.06
     BehaviorSubject
    0.06
     DST
    0.06
     plentiful
    0.06
    ån
    0.06
    uvian
    0.06
    採
    0.06
    Act Density 0.033%

    No Known Activations