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

    Neuronpedia

    INDEX
    Explanations

    numbers and counting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    960
    -0.07
     }},↵
    -0.06
     Active
    -0.06
    ΑΘ
    -0.06
    PER
    -0.06
     Ann
    -0.06
    论文
    -0.06
     Mix
    -0.06
     intervene
    -0.06
     siguientes
    -0.06
    POSITIVE LOGITS
     وف
    0.07
    imde
    0.06
     verdade
    0.06
    .Payload
    0.06
     pouring
    0.06
    rylic
    0.06
     Rever
    0.06
    \base
    0.06
    ософ
    0.06
     portrays
    0.06
    Act Density 0.013%

    No Known Activations