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

    Neuronpedia

    INDEX
    Explanations

    Xml

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .TextUtils
    -0.07
     Gone
    -0.07
    Mag
    -0.07
     складу
    -0.07
     foe
    -0.06
     вмест
    -0.06
    ans
    -0.06
    ्वव
    -0.06
    ]+$
    -0.06
     články
    -0.06
    POSITIVE LOGITS
    UTION
    0.07
     Rath
    0.07
    (wx
    0.07
    Understanding
    0.07
    |{↵
    0.06
    (Q
    0.06
    (prog
    0.06
    imentos
    0.06
     реп
    0.06
     мир
    0.06
    Act Density 0.000%

    No Known Activations