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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nurse
    -0.08
    腑
    -0.07
    瓿
    -0.07
    .setForeground
    -0.07
    _ten
    -0.07
    Ẓ
    -0.07
     mourn
    -0.07
    נוסע
    -0.07
    仅供
    -0.07
     bulun
    -0.07
    POSITIVE LOGITS
    .Handled
    0.08
    '}}↵
    0.07
     }}
↵
    0.07
     ab
    0.06
    (reference
    0.06
    .ForeColor
    0.06
    imits
    0.06
     themes
    0.06
     Ak
    0.06
     confiscated
    0.06
    Act Density 0.001%

    No Known Activations