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

    Neuronpedia

    INDEX
    Explanations

    ingredients or health advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Imaging
    -0.07
    enefit
    -0.06
     Victims
    -0.06
     geographic
    -0.06
     molest
    -0.06
    -angle
    -0.06
     Released
    -0.06
     Equity
    -0.06
     Hazard
    -0.06
    .ask
    -0.06
    POSITIVE LOGITS
     wxT
    0.07
    Bộ
    0.07
     --------------------------------------------------------------------------↵
    0.07
     ACE
    0.06
     추
    0.06
     Vietnamese
    0.06
    多い
    0.06
     unut
    0.06
    TextArea
    0.06
    Об
    0.06
    Act Density 0.012%

    No Known Activations