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

    Neuronpedia

    INDEX
    Explanations

    explaining or describing content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    考えると
    0.34
     akad
    0.33
     kb
    0.33
     ဒီ
    0.33
    ಭಾವ
    0.32
     لان
    0.31
    بت
    0.31
    któ
    0.31
     natürlichen
    0.30
     ursprünglich
    0.30
    POSITIVE LOGITS
     anhand
    0.50
     concisely
    0.46
     firsthand
    0.42
     상세
    0.41
     verbally
    0.40
     подробно
    0.40
     aloud
    0.37
     succinctly
    0.37
    通过
    0.36
    以及
    0.35
    Act Density 0.327%

    No Known Activations