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

    Neuronpedia

    INDEX
    Explanations

    ridiculous kandidat hay barn throwing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Traditions
    0.40
     LEX
    0.38
     Рей
    0.37
    乞
    0.37
    Lex
    0.36
    geon
    0.36
     juris
    0.36
     কৃতজ্ঞ
    0.36
     cheg
    0.35
     LOC
    0.35
    POSITIVE LOGITS
    lhe
    0.41
    بە
    0.38
     Harrow
    0.38
     ll
    0.38
     Arqu
    0.38
     postures
    0.37
     ove
    0.37
    nata
    0.37
     preval
    0.36
    section
    0.36
    Act Density 0.000%

    No Known Activations