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

    Neuronpedia

    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     αδ
    -0.06
     Opcode
    -0.06
     wordt
    -0.06
    elib
    -0.06
    Som
    -0.06
    ーター
    -0.06
     drunken
    -0.06
     Пос
    -0.06
     nz
    -0.06
    .savetxt
    -0.06
    POSITIVE LOGITS
     buttonWithType
    0.07
    _UI
    0.06
    озя
    0.06
    居
    0.06
    utch
    0.06
     ｰ
    0.06
     vie
    0.06
     Tent
    0.06
    สำค
    0.06
    VERY
    0.06
    Act Density 0.015%

    No Known Activations