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

    Neuronpedia

    INDEX
    Explanations

    winfx xsd xml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    thenReturn
    0.41
    骚
    0.40
    FTP
    0.39
     മറ
    0.39
    セキュリティ
    0.38
    つもり
    0.38
    መሪያ
    0.38
    ⅳ
    0.37
    sprites
    0.36
    ftp
    0.36
    POSITIVE LOGITS
     signing
    0.45
     Residence
    0.43
    𝐗
    0.41
     signer
    0.40
     Signing
    0.40
     twin
    0.40
     phim
    0.39
     pointe
    0.39
     signed
    0.39
     Xer
    0.38
    Act Density 0.000%

    No Known Activations