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

    Neuronpedia

    INDEX
    Explanations

    provided

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    者的
    -0.07
     converge
    -0.07
     billboard
    -0.06
     Bureau
    -0.06
     line
    -0.06
     TITLE
    -0.06
     convergence
    -0.06
     parasites
    -0.06
     for
    -0.06
     Lightweight
    -0.06
    POSITIVE LOGITS
    raci
    0.07
     predefined
    0.07
    ilitating
    0.06
    ではなく
    0.06
    Phil
    0.06
    �
    0.06
    фика
    0.06
    ágenes
    0.06
    .variables
    0.06
     PET
    0.06
    Act Density 0.001%

    No Known Activations