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

    Neuronpedia

    INDEX
    Explanations

    Exceptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RL
    -0.06
    assignments
    -0.06
    τις
    -0.06
    Character
    -0.06
    ','#
    -0.06
    searchModel
    -0.06
    .LastName
    -0.06
     Timeline
    -0.06
     décor
    -0.06
    альної
    -0.06
    POSITIVE LOGITS
     esteem
    0.07
     conclusive
    0.07
     Влади
    0.07
     horrors
    0.06
     jewish
    0.06
    ’à
    0.06
     esteemed
    0.06
     Portug
    0.06
    omap
    0.06
     humanity
    0.06
    Act Density 0.000%

    No Known Activations