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

    Neuronpedia

    INDEX
    Explanations

    do justice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     frü
    -0.06
    "]:
    -0.06
     providers
    -0.06
     Layout
    -0.06
    cup
    -0.06
     phosph
    -0.06
    Fake
    -0.06
    avn
    -0.06
     ($)
    -0.06
     degrees
    -0.06
    POSITIVE LOGITS
    getJSON
    0.07
     Trotsky
    0.06
     SAF
    0.06
     Bull
    0.06
    (bottom
    0.06
    banner
    0.06
    (INT
    0.06
    ,true
    0.06
     बद
    0.06
     mex
    0.06
    Act Density 0.031%

    No Known Activations