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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >.</
    -0.07
     humid
    -0.07
     ros
    -0.07
     complic
    -0.06
    ||||
    -0.06
     }</
    -0.06
    )":
    -0.06
    iami
    -0.06
     computations
    -0.06
     html
    -0.06
    POSITIVE LOGITS
    ोप
    0.06
     أكثر
    0.06
    .STATE
    0.06
     طی
    0.06
    бол
    0.06
    @Controller
    0.06
    ント
    0.06
    토토
    0.05
     đó
    0.05
    وا
    0.05
    Act Density 1.930%

    No Known Activations