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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    those
    -0.07
     smrt
    -0.07
     intro
    -0.06
     ents
    -0.06
     Über
    -0.06
     compens
    -0.06
     dissoci
    -0.06
    .mass
    -0.06
     NGO
    -0.06
     Lone
    -0.06
    POSITIVE LOGITS
    423
    0.07
     hotelu
    0.06
     الله
    0.06
     AT
    0.06
    權
    0.06
     Edge
    0.06
     salvage
    0.06
    Bundle
    0.06
    _Invoke
    0.06
    Fax
    0.06
    Act Density 0.027%

    No Known Activations