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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    XmlAccessType
    -0.88
     utafitiHapana
    -0.78
    memoized
    -0.73
    WriteBarrier
    -0.73
     >=",
    -0.72
    Spoljašnje
    -0.72
    StreetMap
    -0.71
    tvguidetime
    -0.69
     Priory
    -0.69
     odkazy
    -0.68
    POSITIVE LOGITS
    веден
    0.40
     gain
    0.39
     comun
    0.38
     dejes
    0.38
    Grants
    0.37
    倖
    0.37
     meeting
    0.36
     terlebih
    0.36
     nämlich
    0.36
    iac
    0.35
    Act Density 0.000%

    No Known Activations