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

    Neuronpedia

    INDEX
    Explanations

    simple capitalization questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Algebra
    0.44
     подрост
    0.43
     adolescents
    0.40
     adoles
    0.40
     algebra
    0.39
    rcl
    0.39
    Minecraft
    0.38
    成年
    0.38
    LCM
    0.38
    ⑬
    0.38
    POSITIVE LOGITS
     pushes
    0.41
     Gamb
    0.39
     Cater
    0.39
     Roberts
    0.39
     fires
    0.39
     simple
    0.38
    uelles
    0.38
     dictate
    0.38
     Ret
    0.37
     stout
    0.37
    Act Density 0.007%

    No Known Activations