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

    Neuronpedia

    INDEX
    Explanations

    secure communication, valuable relationship, focused concentration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上
    0.54
    ബ
    0.51
    ॅ
    0.48
    มอง
    0.47
    א
    0.46
    för
    0.46
    ア
    0.45
    נ
    0.45
    بغ
    0.45
    あ
    0.44
    POSITIVE LOGITS
    li
    0.50
    holder
    0.49
    isini
    0.46
    ere
    0.45
     Milano
    0.44
     Â
    0.43
    ring
    0.42
     pediatric
    0.42
    mip
    0.42
    master
    0.42
    Act Density 0.000%

    No Known Activations