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

    Neuronpedia

    INDEX
    Explanations

    explaining concepts or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getPrice
    0.45
    ádza
    0.44
     predstavlja
    0.43
    тына
    0.41
     آفیسر
    0.40
     требований
    0.39
    剩
    0.39
    rité
    0.39
    मुना
    0.38
     эки
    0.38
    POSITIVE LOGITS
    空白
    0.39
     doors
    0.38
     vesc
    0.38
     /*
    0.37
     весь
    0.36
     eosin
    0.35
     EX
    0.34
    lbrace
    0.34
     mantle
    0.34
     EU
    0.34
    Act Density 0.002%

    No Known Activations