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

    Neuronpedia

    INDEX
    Explanations

    computer science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     THEY
    -0.07
     �
    -0.07
     zien
    -0.07
    дут
    -0.07
    WAR
    -0.07
    .obj
    -0.06
     قطر
    -0.06
     buildup
    -0.06
    @dynamic
    -0.06
     proving
    -0.06
    POSITIVE LOGITS
     Hero
    0.07
     radiator
    0.06
    _exec
    0.06
    etail
    0.06
     volatile
    0.06
    neum
    0.06
     radial
    0.06
    营
    0.06
    atile
    0.06
    contracts
    0.06
    Act Density 0.000%

    No Known Activations