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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .j
    -0.07
    avn
    -0.06
    .keras
    -0.06
     depressed
    -0.06
    ㆍ동
    -0.06
     steril
    -0.06
     jejich
    -0.06
     attendee
    -0.06
    基
    -0.06
    -line
    -0.06
    POSITIVE LOGITS
     hé
    0.07
    =:
    0.06
    eci
    0.06
    nické
    0.06
    šek
    0.06
    ایج
    0.06
     Rena
    0.06
    े।
    0.06
    _PHYS
    0.06
     Charg
    0.06
    Act Density 0.042%

    No Known Activations