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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belasting
    -0.09
     ling
    -0.08
     recruitment
    -0.08
     scouts
    -0.07
    .ag
    -0.07
    ขึ้น
    -0.07
     एज
    -0.07
     Recruitment
    -0.07
     metadata
    -0.07
     requis
    -0.07
    POSITIVE LOGITS
     despair
    0.10
    subtract
    0.10
    Subtract
    0.10
    掉
    0.10
    .subtract
    0.09
     subtract
    0.09
     �
    0.08
     disappointment
    0.08
    /add
    0.08
     unsere
    0.08
    Act Density 0.181%

    No Known Activations