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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slide
    -0.07
    124
    -0.07
    .Web
    -0.07
    017
    -0.07
    652
    -0.07
    -down
    -0.07
    izer
    -0.06
    naissance
    -0.06
    /java
    -0.06
    .Parameters
    -0.06
    POSITIVE LOGITS
     біль
    0.07
     Victim
    0.07
    .asset
    0.07
     iNdEx
    0.06
     myšlen
    0.06
    .layoutControl
    0.06
    .getError
    0.06
     треб
    0.06
     odkazy
    0.06
    -eng
    0.06
    Act Density 0.016%

    No Known Activations