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
    226
    -0.08
    าคาร
    -0.07
     Tb
    -0.07
    ruk
    -0.07
     dubbed
    -0.07
    iazza
    -0.06
     baggage
    -0.06
    风险
    -0.06
    ComboBox
    -0.06
     Homes
    -0.06
    POSITIVE LOGITS
     COMPANY
    0.06
    >}↵
    0.06
    flowers
    0.06
    ]';↵
    0.06
    Composer
    0.06
    Krist
    0.06
    mid
    0.06
    .extract
    0.06
     <
    0.05
     Những
    0.05
    Act Density 0.004%

    No Known Activations