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

    Neuronpedia

    INDEX
    Explanations

    narrow down a selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     প্রতিটি
    0.46
     každý
    0.45
     chacun
    0.45
     каждый
    0.44
    each
    0.44
    both
    0.44
    ißler
    0.44
     hver
    0.44
    agnar
    0.43
     chacune
    0.42
    POSITIVE LOGITS
     among
    1.24
     parmi
    1.22
     amongst
    1.13
     среди
    1.13
     wśród
    1.13
    Among
    1.12
    among
    1.06
     Among
    1.05
    śród
    0.96
     dentre
    0.93
    Act Density 0.010%

    No Known Activations