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

    Neuronpedia

    INDEX
    Explanations

    Pinterest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     May
    -0.08
     excerpts
    -0.07
     endorsing
    -0.07
    ﺄ
    -0.07
    ’aut
    -0.07
     PARAMETERS
    -0.07
    obre
    -0.07
    -area
    -0.07
    _DATABASE
    -0.07
    (AdapterView
    -0.07
    POSITIVE LOGITS
     Pinterest
    0.07
     ~
    0.07
    꼼
    0.07
    🛡
    0.07
     charged
    0.07
    一半
    0.07
    lz
    0.06
    列为
    0.06
     reported
    0.06
    مطل
    0.06
    Act Density 0.002%

    No Known Activations