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

    Neuronpedia

    INDEX
    Explanations

    learned

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Organizations
    -0.08
     Smith
    -0.07
     Legislature
    -0.07
     manufactures
    -0.06
     smartphones
    -0.06
    ceeded
    -0.06
     deductible
    -0.06
     Anal
    -0.06
     Applicant
    -0.06
     terör
    -0.06
    POSITIVE LOGITS
     раб
    0.07
     �
    0.07
    _PERSON
    0.06
     공동
    0.06
    _DEC
    0.06
     osoby
    0.06
     gast
    0.06
     AN
    0.06
    birthday
    0.06
     UIAlertAction
    0.06
    Act Density 0.079%

    No Known Activations