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

    Neuronpedia

    INDEX
    Explanations

    `based` `and` `January` `fueron`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     emble
    0.53
    MacOS
    0.51
     pubblica
    0.50
    नमस्कार
    0.50
    及び
    0.48
    Sunny
    0.48
     Mén
    0.48
     Forma
    0.47
    VII
    0.46
    På
    0.46
    POSITIVE LOGITS
     दाख
    0.50
     эр
    0.49
    𝘵
    0.47
    𝑙
    0.45
    𝓈
    0.44
    𝘯
    0.44
    𝘭
    0.44
     الص
    0.44
    ות
    0.43
     পাখ
    0.42
    Act Density 0.000%

    No Known Activations