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

    Neuronpedia

    INDEX
    Explanations

    absolutely critical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ik
    1.08
    되는
    1.07
    বহুল
    1.06
    pues
    1.01
    很好的
    1.00
    ера
    0.99
     easily
    0.98
    良好的
    0.98
    es
    0.96
    NaOMe
    0.95
    POSITIVE LOGITS
    𝐝
    1.27
     notwendig
    1.14
    ্টার
    1.14
    nothing
    1.13
    CHN
    1.13
    minute
    1.13
     nothing
    1.12
     decked
    1.12
     replete
    1.09
    勝
    1.09
    Act Density 0.060%

    No Known Activations