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

    Neuronpedia

    INDEX
    Explanations

    cause

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     objectType
    -0.07
     trays
    -0.06
    emales
    -0.06
     Sonra
    -0.06
    랜드
    -0.06
     neboť
    -0.06
    wrong
    -0.06
    ces
    -0.06
     Soros
    -0.06
    loh
    -0.06
    POSITIVE LOGITS
    .wall
    0.08
    .Json
    0.07
     separator
    0.07
    /stream
    0.06
    "%(
    0.06
    /archive
    0.06
    =""/>↵
    0.06
     SMS
    0.06
    .utils
    0.06
    .purchase
    0.06
    Act Density 0.032%

    No Known Activations