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

    Neuronpedia

    INDEX
    Explanations

    categorizing by "for"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     offrire
    0.52
     obtainable
    0.51
     bijvoorbeeld
    0.49
     attainable
    0.49
    фии
    0.49
     soles
    0.48
     las
    0.48
     females
    0.48
     gemakkelijk
    0.47
     హీరోయి
    0.47
    POSITIVE LOGITS
    Session
    0.50
    Hor
    0.50
    璋
    0.49
    ومت
    0.49
    Smith
    0.48
    Spark
    0.47
    Sandbox
    0.47
     شم
    0.46
    Light
    0.45
    Flow
    0.45
    Act Density 0.002%

    No Known Activations