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

    Neuronpedia

    INDEX
    Explanations

    tournaments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cat
    -0.07
    ewire
    -0.07
    VI
    -0.07
     Format
    -0.07
     dominant
    -0.07
     falsely
    -0.06
     STREAM
    -0.06
     Tomorrow
    -0.06
    FRING
    -0.06
     musique
    -0.06
    POSITIVE LOGITS
    icion
    0.07
     fov
    0.06
    нице
    0.06
    .DockStyle
    0.06
     CCT
    0.06
     зроб
    0.06
     poměrně
    0.06
    .relative
    0.06
    nid
    0.06
     Как
    0.06
    Act Density 0.015%

    No Known Activations