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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thoát
    -0.07
    .Format
    -0.07
    tiny
    -0.07
    entů
    -0.06
    âte
    -0.06
    이며
    -0.06
     secretive
    -0.06
    率
    -0.06
    myp
    -0.06
    िग
    -0.06
    POSITIVE LOGITS
     совет
    0.07
    .defaultValue
    0.07
     DPS
    0.07
     Republican
    0.06
     entreprise
    0.06
    IRD
    0.06
     orbit
    0.06
    _cal
    0.06
    Mari
    0.06
    .population
    0.06
    Act Density 0.014%

    No Known Activations