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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crane
    -0.08
    स्
    -0.08
    وية
    -0.08
     Grim
    -0.07
    ക്ക്
    -0.07
     padr
    -0.07
     planos
    -0.07
    لفة
    -0.07
     fog
    -0.07
     Lisp
    -0.07
    POSITIVE LOGITS
    econom
    0.09
     교수
    0.08
     Tehran
    0.08
     преподав
    0.07
     fashion
    0.07
     stood
    0.07
    engeance
    0.07
    Econom
    0.07
     teachers
    0.07
     اقتصاد
    0.07
    Act Density 0.007%

    No Known Activations