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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _nbr
    -0.07
    ustering
    -0.07
     modular
    -0.07
     Sirius
    -0.07
     junit
    -0.06
     بشر
    -0.06
     '&'
    -0.06
     pacman
    -0.06
     wereld
    -0.06
    anco
    -0.06
    POSITIVE LOGITS
    iane
    0.07
    Tes
    0.06
        
    0.06
     syntax
    0.06
    .Must
    0.06
     qui
    0.06
    Smoke
    0.06
    _usage
    0.06
    ущ
    0.06
    eresa
    0.06
    Act Density 0.002%

    No Known Activations