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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρίου
    -0.07
     IDENT
    -0.07
     lut
    -0.07
    ARB
    -0.07
     Logs
    -0.06
    Pretty
    -0.06
    ems
    -0.06
    .Roles
    -0.06
     isFirst
    -0.06
     stagger
    -0.06
    POSITIVE LOGITS
     Alman
    0.07
     kısm
    0.06
     Playlist
    0.06
     pushes
    0.06
    개
    0.06
     Femme
    0.06
    swing
    0.06
    シリーズ
    0.06
     tượng
    0.06
    ầy
    0.06
    Act Density 0.026%

    No Known Activations