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

    Neuronpedia

    INDEX
    Explanations

    block

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AUTHORITY
    0.44
     ऑड
    0.40
    䡈
    0.40
    醫師
    0.39
     내용은
    0.38
     সূর্য
    0.38
     причины
    0.38
     Sury
    0.38
    みた
    0.37
     नगरपालिका
    0.37
    POSITIVE LOGITS
     bloc
    0.39
    azolin
    0.39
    BLK
    0.39
     preoccupation
    0.37
    Bloc
    0.37
    блоки
    0.37
    0.37
    outing
    0.36
    violent
    0.35
    、​
    0.35
    Act Density 0.000%

    No Known Activations