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

    Neuronpedia

    INDEX
    Explanations

    its plus descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     их
    1.26
     themselves
    1.21
     їх
    1.18
     kanilang
    1.15
     Они
    1.14
     identities
    1.08
     Their
    1.07
    他们在
    1.05
    他們
    1.05
     которые
    1.04
    POSITIVE LOGITS
    它的
    1.26
    elf
    1.19
    ರ್ಥ
    1.01
    ik
    1.00
     entirety
    1.00
    erms
    0.98
    utorial
    0.98
    alic
    0.97
    utom
    0.96
    रीज
    0.96
    Act Density 0.096%

    No Known Activations