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
     Plates
    -0.07
     staircase
    -0.07
    �
    -0.07
     Manchester
    -0.07
     outlaw
    -0.06
     Beet
    -0.06
    -IS
    -0.06
    CPP
    -0.06
    ंटर
    -0.06
     dragged
    -0.06
    POSITIVE LOGITS
    <string
    0.07
    атов
    0.06
     integral
    0.06
    .Sprintf
    0.06
     elect
    0.06
    ามารถ
    0.06
     [{'
    0.06
     tard
    0.06
    _{
    0.06
    /string
    0.06
    Act Density 0.039%

    No Known Activations