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

    Neuronpedia

    INDEX
    Explanations

    grammar explanations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وإ
    -0.07
    تجاوز
    -0.07
    ians
    -0.07
     sacred
    -0.07
     אסור
    -0.07
     artery
    -0.07
     translating
    -0.06
     compiling
    -0.06
     airports
    -0.06
    תוך
    -0.06
    POSITIVE LOGITS
    沃尔沃
    0.08
    ﻠ
    0.07
     unve
    0.07
    slideDown
    0.07
    BB
    0.07
     Pivot
    0.06
    �
    0.06
    펄
    0.06
    �
    0.06
     reli
    0.06
    Act Density 0.023%

    No Known Activations