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

    Neuronpedia

    INDEX
    Explanations

    mongoose or Oops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uly
    0.43
    egd
    0.40
    olai
    0.39
    gives
    0.38
    imli
    0.38
    0.38
    打
    0.38
    willReturn
    0.38
    Nap
    0.38
    ইহার
    0.37
    POSITIVE LOGITS
     Reader
    0.40
     B
    0.39
     (;
    0.38
    欒
    0.38
     tiến
    0.38
     Rif
    0.38
     studying
    0.36
     Questions
    0.36
     connected
    0.35
     connective
    0.35
    Act Density 0.000%

    No Known Activations