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

    Neuronpedia

    INDEX
    Explanations

    Code and math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     setzen
    -0.07
    ]])
    -0.07
     NSK
    -0.06
     Toshiba
    -0.06
    .jwt
    -0.06
    ="#"><
    -0.06
    .Quantity
    -0.06
     matt
    -0.06
    %"><
    -0.06
     З
    -0.06
    POSITIVE LOGITS
    unct
    0.07
     krist
    0.07
     witnesses
    0.07
     Joh
    0.07
    .handler
    0.06
    含
    0.06
    ,map
    0.06
    (dot
    0.06
     articulated
    0.06
    fan
    0.06
    Act Density 0.000%

    No Known Activations