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

    Neuronpedia

    INDEX
    Explanations

    open source or free

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .heroku
    -0.11
    .oracle
    -0.10
     Safari
    -0.10
     Cary
    -0.10
    ety
    -0.10
     Nim
    -0.10
     terra
    -0.09
     FTP
    -0.09
     zd
    -0.09
    .Obj
    -0.09
    POSITIVE LOGITS
     Open
    0.21
     open
    0.17
    Open
    0.15
    open
    0.13
     Koh
    0.13
    -open
    0.13
     Sugar
    0.13
     Açık
    0.12
     Pent
    0.12
     Free
    0.11
    Act Density 0.152%

    No Known Activations