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

    Neuronpedia

    INDEX
    Explanations

    challenges, process, inadvertently

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᱠ
    0.44
    innerApiCalls
    0.44
    セプト
    0.44
    0.41
    setwd
    0.41
     Justiça
    0.41
    überküloz
    0.41
     abusing
    0.40
     censoring
    0.40
     antigüedad
    0.40
    POSITIVE LOGITS
     capabilities
    0.42
    దారు
    0.41
     WON
    0.40
     micró
    0.39
     hoof
    0.38
     দুনি
    0.38
    哠
    0.38
     ул
    0.38
     castor
    0.38
     quite
    0.38
    Act Density 0.004%

    No Known Activations