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

    Neuronpedia

    INDEX
    Explanations

    information you provide to commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     наро
    0.46
    ار
    0.46
    徝
    0.45
    віт
    0.44
    แต่ละ
    0.44
     Перейти
    0.44
     Felt
    0.43
    ור
    0.43
     Amman
    0.42
    खिक
    0.42
    POSITIVE LOGITS
     name
    0.42
    人に
    0.42
     limestone
    0.40
    leye
    0.40
     চি
    0.40
     facile
    0.40
     bateria
    0.40
    නේ
    0.40
     fabulous
    0.39
     calcium
    0.39
    Act Density 0.001%

    No Known Activations