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
     efekt
    -0.07
     Animal
    -0.06
     طرف
    -0.06
     excellence
    -0.06
    license
    -0.06
     cleanup
    -0.06
     queries
    -0.06
    -gen
    -0.06
     prepare
    -0.06
     blends
    -0.06
    POSITIVE LOGITS
     معدن
    0.07
    _years
    0.06
     accompany
    0.06
    _reservation
    0.06
     McG
    0.06
     централь
    0.06
     Riot
    0.06
    operative
    0.06
    (inv
    0.06
    �
    0.06
    Act Density 0.036%

    No Known Activations