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

    Neuronpedia

    INDEX
    Explanations

    place

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -but
    -0.07
    word
    -0.07
    both
    -0.07
     hemisphere
    -0.07
    seudo
    -0.07
     Sharma
    -0.07
     domestic
    -0.06
    estic
    -0.06
     recreation
    -0.06
    制
    -0.06
    POSITIVE LOGITS
     значительно
    0.07
     tremend
    0.06
     brainstorm
    0.06
     масс
    0.06
     fund
    0.06
    (tb
    0.06
    (CONFIG
    0.06
     staat
    0.06
     License
    0.06
    (Element
    0.06
    Act Density 0.004%

    No Known Activations