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

    Neuronpedia

    INDEX
    Explanations

    coolness and sensory feel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NAME
    0.43
     বিবৃতিতে
    0.40
    ケーション
    0.39
     названия
    0.38
    Anything
    0.37
    ilium
    0.37
    crib
    0.36
    寄せ
    0.36
    anything
    0.36
    visible
    0.35
    POSITIVE LOGITS
     salesman
    0.41
     korean
    0.39
     salespeople
    0.39
     seawater
    0.38
     octobre
    0.38
     mathematic
    0.38
     salesmen
    0.38
     mucous
    0.37
     নীলন
    0.37
     salesperson
    0.36
    Act Density 0.002%

    No Known Activations