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

    Neuronpedia

    INDEX
    Explanations

    detail pages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    발
    0.39
     ISP
    0.38
     OTP
    0.36
    #(
    0.36
     ease
    0.35
    肛
    0.34
     গিয়েছে
    0.34
     एसपी
    0.34
     cosmetology
    0.34
     GetData
    0.33
    POSITIVE LOGITS
    ব্ল
    0.39
     yanında
    0.38
     wundersch
    0.37
     queen
    0.37
     অঞ্চল
    0.36
    outheast
    0.35
     প্রতির
    0.35
     प्रवाह
    0.35
    elerde
    0.35
    ğlu
    0.35
    Act Density 0.001%

    No Known Activations