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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SPACE
    -0.06
    ocaly
    -0.06
    ิทยาศาสตร
    -0.06
    (clone
    -0.06
     kıy
    -0.06
    _nr
    -0.06
     لكن
    -0.06
    rhs
    -0.05
    lardı
    -0.05
    .ylabel
    -0.05
    POSITIVE LOGITS
    追加
    0.07
    склад
    0.07
     Sag
    0.07
     Granite
    0.06
    сяч
    0.06
     Trash
    0.06
     transpose
    0.06
     Lopez
    0.06
    ือด
    0.06
     strong
    0.06
    Act Density 0.103%

    No Known Activations