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

    Neuronpedia

    INDEX
    Explanations

    existential arguments and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rystall
    0.49
    oxide
    0.47
    ind
    0.47
    kari
    0.47
    crystalline
    0.47
    municipal
    0.44
    odo
    0.44
    ashed
    0.44
    thank
    0.43
    german
    0.43
    POSITIVE LOGITS
     있지만
    0.47
     Comparisons
    0.41
     Eindruck
    0.41
     Workflow
    0.40
     Play
    0.40
    しますが
    0.40
     می‌کن
    0.40
     Interchange
    0.39
     موتور
    0.39
    ましたが
    0.39
    Act Density 0.013%

    No Known Activations