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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ΔΗΜ
    -0.07
    ppo
    -0.06
    ์โ
    -0.06
    wstring
    -0.06
    .resource
    -0.06
     Hawai
    -0.06
    .games
    -0.06
     astronomy
    -0.06
     nutzen
    -0.06
    -document
    -0.06
    POSITIVE LOGITS
     secretary
    0.07
    请
    0.07
    slideDown
    0.06
     λο
    0.06
    _pll
    0.06
    	remove
    0.06
    795
    0.06
     Heg
    0.06
    (dot
    0.06
    (thing
    0.06
    Act Density 0.000%

    No Known Activations