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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ileaks
    -0.07
     एन
    -0.07
    áln
    -0.07
     depreciation
    -0.07
    .idx
    -0.06
    factor
    -0.06
     친
    -0.06
     alice
    -0.06
     прок
    -0.06
    	count
    -0.06
    POSITIVE LOGITS
    atham
    0.07
    optional
    0.07
     Erie
    0.06
    _Map
    0.06
    _result
    0.06
    �
    0.06
    Benchmark
    0.06
    更
    0.06
    日本
    0.06
    ----</
    0.06
    Act Density 0.020%

    No Known Activations