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

    Neuronpedia

    INDEX
    Explanations

    competition/achievement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     broker
    -0.07
     DW
    -0.06
     mount
    -0.06
     dan
    -0.06
     Alexander
    -0.06
     Heller
    -0.06
     Wer
    -0.06
    河
    -0.06
     fruit
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _OP
    0.07
    _large
    0.06
    _encoder
    0.06
    ...')↵
    0.06
    IQ
    0.06
     -↵↵
    0.06
    .codehaus
    0.06
    (UnmanagedType
    0.06
    Producto
    0.06
     ее
    0.06
    Act Density 1.572%

    No Known Activations