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

    Neuronpedia

    INDEX
    Explanations

    value

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blacklist
    -0.07
     poc
    -0.07
    ních
    -0.06
     Sanctuary
    -0.06
    (bytes
    -0.06
    路径
    -0.06
    .Duration
    -0.06
     ned
    -0.06
    GROUP
    -0.06
     상황
    -0.06
    POSITIVE LOGITS
     mtx
    0.07
     snacks
    0.06
    ,(
    0.06
    reports
    0.06
     verts
    0.06
     が
    0.06
     traj
    0.06
     صد
    0.06
     สล
    0.06
     Kap
    0.06
    Act Density 0.003%

    No Known Activations