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

    Neuronpedia

    INDEX
    Explanations

    diverse text datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Common
    0.43
     Citizens
    0.42
     πό
    0.41
     شدید
    0.39
     INDIRECT
    0.38
    ौल
    0.37
    Common
    0.36
    estell
    0.36
    COMMON
    0.36
    ėd
    0.35
    POSITIVE LOGITS
     रत्
    0.41
     letters
    0.38
    Rainbow
    0.37
     glitches
    0.37
    clouds
    0.36
     grinders
    0.36
     gild
    0.36
     nic
    0.36
     gardens
    0.36
    gå
    0.36
    Act Density 0.005%

    No Known Activations