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

    Neuronpedia

    INDEX
    Explanations

    database find operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etrically
    0.46
     intuitively
    0.44
     allere
    0.42
    ifically
    0.42
     shrinks
    0.41
     painters
    0.40
    cedes
    0.40
     shrunk
    0.40
     chiefly
    0.39
     already
    0.39
    POSITIVE LOGITS
    Kayak
    0.45
     شركات
    0.43
    Yah
    0.39
     방법을
    0.38
    jekte
    0.37
     عشق
    0.37
    DU
    0.36
    Cliente
    0.36
    場合がございます
    0.36
    سٹم
    0.36
    Act Density 0.000%

    No Known Activations