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

    Neuronpedia

    INDEX
    Explanations

    US cities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ፩
    0.43
     độ
    0.40
    Combined
    0.39
    ബ്ര
    0.39
    想
    0.38
    طاء
    0.38
     quadr
    0.38
     Hartman
    0.37
    דור
    0.37
    ỏng
    0.37
    POSITIVE LOGITS
     Wisconsin
    0.43
     Milwaukee
    0.41
    kit
    0.40
     californ
    0.40
     Nashville
    0.40
     مك
    0.40
     Tennessee
    0.38
     congenial
    0.38
     PROBLE
    0.37
    EFF
    0.37
    Act Density 0.001%

    No Known Activations