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

    Neuronpedia

    INDEX
    Explanations

    economy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Дмит
    -0.06
    ocomplete
    -0.06
    MU
    -0.06
    循
    -0.06
    692
    -0.06
     wires
    -0.06
    bras
    -0.06
     programas
    -0.06
    شة
    -0.06
     annoyed
    -0.05
    POSITIVE LOGITS
    릭
    0.06
     dementia
    0.06
     Gambling
    0.06
     trip
    0.06
     rects
    0.06
    glich
    0.06
     enfer
    0.06
    ブル
    0.06
    Going
    0.06
     trusted
    0.06
    Act Density 0.022%

    No Known Activations