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

    Neuronpedia

    INDEX
    Explanations

    Feynman Method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    vd
    -0.08
    ubes
    -0.07
    sqrt
    -0.07
    fluid
    -0.07
    excluding
    -0.07
    вет
    -0.07
     Rays
    -0.07
     acknowledges
    -0.07
     acknowledge
    -0.07
     suplementos
    -0.07
    POSITIVE LOGITS
     Persona
    0.09
     õpet
    0.09
     Técnica
    0.09
     Teach
    0.09
    เด็ก
    0.09
     Teaching
    0.08
     শেখ
    0.08
    নীতি
    0.08
     শিশু
    0.08
     শিক্ষক
    0.08
    Act Density 0.001%

    No Known Activations