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

    Neuronpedia

    INDEX
    Explanations

    line

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jours
    -0.06
    Mech
    -0.06
    .DataSource
    -0.06
    ーフ
    -0.06
     Télé
    -0.06
    igmoid
    -0.06
    ise
    -0.06
     Danh
    -0.06
     Joy
    -0.06
    글상위
    -0.06
    POSITIVE LOGITS
    писание
    0.07
     VARIABLES
    0.07
     skincare
    0.07
    [data
    0.07
    [X
    0.07
     icy
    0.06
     Mega
    0.06
    ($
    0.06
     incarcerated
    0.06
     цер
    0.06
    Act Density 0.015%

    No Known Activations