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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ut
    -0.06
     dissoci
    -0.06
     У
    -0.06
    Parents
    -0.06
    Em
    -0.06
    gui
    -0.06
    сем
    -0.06
    Major
    -0.06
    -dir
    -0.06
    プ
    -0.06
    POSITIVE LOGITS
    瓦
    0.07
     Vinyl
    0.06
     dominate
    0.06
     вина
    0.06
     sofa
    0.06
     honda
    0.06
     TOO
    0.06
    /meta
    0.06
     variability
    0.06
     Castro
    0.06
    Act Density 0.022%

    No Known Activations