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

    Neuronpedia

    INDEX
    Explanations

    Escape/control characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bonds
    -0.07
    Insets
    -0.07
    ैस
    -0.06
     preference
    -0.06
     capitalize
    -0.06
     Index
    -0.06
    لاث
    -0.06
    Needed
    -0.06
    inema
    -0.06
     rampage
    -0.06
    POSITIVE LOGITS
     इसम
    0.06
     จำนวน
    0.06
    play
    0.06
     ولي
    0.06
    TEL
    0.06
     Tian
    0.06
     rtl
    0.06
    (USER
    0.06
    /GL
    0.06
     lorsque
    0.06
    Act Density 0.017%

    No Known Activations