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

    Neuronpedia

    INDEX
    Explanations

    safe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zák
    -0.09
     पुरस्कार
    -0.08
     diversidade
    -0.08
     nyik
    -0.08
     diversity
    -0.08
     advocating
    -0.08
     recogn
    -0.08
     twice
    -0.08
    òs
    -0.08
     désormais
    -0.08
    POSITIVE LOGITS
     isolate
    0.11
     isolates
    0.10
     Isolation
    0.10
     Simpl
    0.09
     isol
    0.09
     aisl
    0.09
    Isolation
    0.09
     narrowed
    0.09
     ಪರೀಕ್ಷ
    0.09
     isolamento
    0.09
    Act Density 0.007%

    No Known Activations