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

    Neuronpedia

    INDEX
    Explanations

    species of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     esters
    0.52
     também
    0.51
     pollutant
    0.49
     pollutants
    0.47
     postulates
    0.46
     legumes
    0.45
     nas
    0.45
     estoppel
    0.45
     imputation
    0.45
     endpoints
    0.44
    POSITIVE LOGITS
    0
    0.56
    7
    0.47
    2
    0.46
     Holmes
    0.46
    Multiply
    0.44
    <tr>
    0.41
    printing
    0.41
    த்த
    0.40
    6
    0.40
    حل
    0.39
    Act Density 0.002%

    No Known Activations