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

    Neuronpedia

    INDEX
    Explanations

    data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (seed
    -0.08
    QE
    -0.07
    pressed
    -0.07
     suo
    -0.07
     Allied
    -0.06
     speaker
    -0.06
    nač
    -0.06
     myfile
    -0.06
    IDD
    -0.06
     Chen
    -0.06
    POSITIVE LOGITS
    $args
    0.06
    luet
    0.06
    groupBox
    0.06
    ，让
    0.06
     �
    0.06
    -month
    0.06
    etting
    0.06
    }}>
    0.06
    예
    0.06
     برنامه
    0.06
    Act Density 0.062%

    No Known Activations