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

    Neuronpedia

    INDEX
    Explanations

    America

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bond
    -0.07
    Seek
    -0.07
     unwilling
    -0.07
     HARD
    -0.07
    秉
    -0.06
    abyrin
    -0.06
    -school
    -0.06
    -hour
    -0.06
    .leave
    -0.06
     port
    -0.06
    POSITIVE LOGITS
     decking
    0.07
     offsetY
    0.07
    -interface
    0.07
    (slice
    0.06
    뿐만
    0.06
    (`${
    0.06
    𫄨
    0.06
    ignet
    0.06
    ද
    0.06
    ∤
    0.06
    Act Density 0.872%

    No Known Activations