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

    Neuronpedia

    INDEX
    Explanations

    software packages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doctor
    -0.07
     upright
    -0.06
     branding
    -0.06
    udies
    -0.06
    ADR
    -0.06
     Qin
    -0.06
    och
    -0.06
    .EXTRA
    -0.06
    546
    -0.06
     moral
    -0.06
    POSITIVE LOGITS
    _Position
    0.07
    .None
    0.07
     ná
    0.06
    】↵
    0.06
     css
    0.06
     LOG
    0.06
     аж
    0.06
    ORIZED
    0.06
     ölçü
    0.06
    (disposing
    0.06
    Act Density 0.041%

    No Known Activations