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

    Neuronpedia

    INDEX
    Explanations

    time indicators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    细胞
    -0.06
    itivity
    -0.06
     dissoci
    -0.06
    ieron
    -0.06
     Partner
    -0.06
    tam
    -0.06
     يتم
    -0.06
     cứ
    -0.06
     develops
    -0.06
     develop
    -0.06
    POSITIVE LOGITS
     fal
    0.07
    toHave
    0.07
     last
    0.06
    linewidth
    0.06
    .workflow
    0.06
    lacak
    0.06
     ACTIONS
    0.06
    Last
    0.06
    .Shape
    0.06
    horia
    0.06
    Act Density 0.081%

    No Known Activations