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

    Neuronpedia

    INDEX
    Explanations

    introducing explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     valves
    0.40
     wafer
    0.38
     productColor
    0.38
     panes
    0.38
     dermal
    0.38
     checkbox
    0.37
    按钮
    0.36
     wafers
    0.36
    чком
    0.36
     vetor
    0.36
    POSITIVE LOGITS
     Moreover
    0.50
     Furthermore
    0.46
     While
    0.45
     It
    0.45
     However
    0.44
     Additionally
    0.43
     Specifically
    0.43
     Although
    0.42
     Inoltre
    0.42
     Ayrıca
    0.42
    Act Density 0.552%

    No Known Activations