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

    Neuronpedia

    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gases
    -0.07
    當
    -0.07
     diarrhea
    -0.06
    familia
    -0.06
    .Double
    -0.06
    Activity
    -0.06
     knife
    -0.06
     testcase
    -0.06
    Monkey
    -0.06
     correlates
    -0.06
    POSITIVE LOGITS
    annual
    0.06
     vlast
    0.06
    �
    0.06
    ————————
    0.06
    SerializedName
    0.06
    (comb
    0.06
     progn
    0.06
     Госп
    0.06
    rounded
    0.06
    ンティ
    0.06
    Act Density 0.270%

    No Known Activations