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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _entries
    -0.07
    (Id
    -0.07
     Bij
    -0.07
    vang
    -0.07
     às
    -0.06
    антаж
    -0.06
     αγα
    -0.06
    /bg
    -0.06
     Role
    -0.06
     decrypt
    -0.06
    POSITIVE LOGITS
    春
    0.08
    ,N
    0.07
    無料
    0.06
    WN
    0.06
    Philadelphia
    0.06
    AILY
    0.06
     труда
    0.06
    excerpt
    0.06
    -trained
    0.06
    �
    0.06
    Act Density 0.002%

    No Known Activations