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

    Neuronpedia

    INDEX
    Explanations

    web links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     વિદ
    0.43
    visually
    0.40
    ऐसा
    0.40
    careers
    0.39
    ledge
    0.38
    Mike
    0.37
    }//
    0.37
     причи
    0.37
    从中
    0.37
    www
    0.37
    POSITIVE LOGITS
     പൊലീസ്
    0.42
     pthread
    0.41
     rescuing
    0.39
     hydroxyl
    0.39
    iological
    0.38
     contraband
    0.38
    mä
    0.37
     faculties
    0.37
     nontrivial
    0.37
     গুগল
    0.37
    Act Density 0.000%

    No Known Activations