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

    Neuronpedia

    INDEX
    Explanations

    Possessive articles/pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Territory
    -0.08
    요
    -0.07
     nghị
    -0.07
     --
    -0.07
    адж
    -0.07
     measured
    -0.06
    (pred
    -0.06
     monitoring
    -0.06
    (Status
    -0.06
    ('
    -0.06
    POSITIVE LOGITS
     disbelief
    0.07
     adına
    0.06
     ive
    0.06
     Aqua
    0.06
     bì
    0.06
     Substitute
    0.06
     JAXBElement
    0.06
    Activated
    0.06
     cancelButton
    0.06
    _F
    0.06
    Act Density 0.045%

    No Known Activations