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

    Neuronpedia

    INDEX
    Explanations

    words related to quality, manufacturing processes, and health, or words used in a modal phrase

    oai_token-act-pair · gemini-2.0-flash

    suffer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    спла
    -0.55
    abestanden
    -0.51
     برانيه
    -0.50
     africains
    -0.48
    brug
    -0.46
     verteilt
    -0.46
     bezeichneter
    -0.45
     initComponents
    -0.44
    Sziasztok
    -0.43
     volna
    -0.43
    POSITIVE LOGITS
     suffer
    1.30
     suffers
    1.21
     Suffer
    1.10
     suffering
    1.05
     suffered
    0.98
     Suffering
    0.97
    suffering
    0.96
     Roskov
    0.88
     sufferings
    0.78
     sufferer
    0.71
    Act Density 1.775%

    No Known Activations