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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Metric
    -0.07
    输
    -0.07
    liquid
    -0.06
    istrib
    -0.06
     liquid
    -0.06
     autob
    -0.06
    位置
    -0.06
     flam
    -0.06
    ，将
    -0.06
     recess
    -0.06
    POSITIVE LOGITS
     Doyle
    0.08
    _do
    0.07
     DO
    0.07
    ující
    0.07
    fighters
    0.07
    earable
    0.07
     handwritten
    0.07
     DONE
    0.07
    eği
    0.07
    implemented
    0.07
    Act Density 0.014%

    No Known Activations