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

    Neuronpedia

    INDEX
    Explanations

    potential and possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gover
    0.28
    interactions
    0.23
    assessment
    0.22
    মে
    0.22
    employment
    0.21
    interaction
    0.21
    collection
    0.21
    evaluation
    0.21
    Contains
    0.21
    ர்
    0.21
    POSITIVE LOGITS
     easily
    0.34
     withstand
    0.32
     afford
    0.32
     tolerate
    0.30
     accommodate
    0.29
     fácilmente
    0.29
     confidently
    0.28
     facilement
    0.27
     manipulate
    0.27
     muster
    0.27
    Act Density 0.081%

    No Known Activations