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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ::
    -0.09
    Saf
    -0.08
     loose
    -0.08
     welcoming
    -0.07
     समर्थ
    -0.07
     being
    -0.07
    frag
    -0.07
     properties
    -0.07
     pand
    -0.07
    being
    -0.07
    POSITIVE LOGITS
     blem
    0.12
     repercussions
    0.11
     unemployment
    0.10
     adversely
    0.10
     Worse
    0.09
     Records
    0.09
     setback
    0.09
     Employers
    0.09
    。でも
    0.09
     incurred
    0.09
    Act Density 0.045%

    No Known Activations