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

    Neuronpedia

    INDEX
    Explanations

    say periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     רחב
    -0.07
    裱
    -0.07
     basically
    -0.07
    ธนา
    -0.07
    êm
    -0.07
     có
    -0.07
     decentralized
    -0.06
     extrapol
    -0.06
     término
    -0.06
    ﮤ
    -0.06
    POSITIVE LOGITS
     student
    0.07
    -seven
    0.07
    neas
    0.07
    חיל
    0.07
    Lines
    0.07
     neck
    0.06
     rights
    0.06
     cleared
    0.06
     prototypes
    0.06
    ()<<
    0.06
    Act Density 0.003%

    No Known Activations