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

    Neuronpedia

    INDEX
    Explanations

    as, mention, with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shay
    -0.07
     TPP
    -0.06
    ManagedObject
    -0.06
    ookeeper
    -0.06
    Model
    -0.06
    ablo
    -0.06
    нист
    -0.06
    Claims
    -0.06
    들이
    -0.06
     пло
    -0.06
    POSITIVE LOGITS
     �
    0.07
     muttered
    0.07
    _GB
    0.06
    atrice
    0.06
    _chat
    0.06
     handy
    0.06
     ліс
    0.06
    AYOUT
    0.06
     ".$_
    0.06
     phận
    0.06
    Act Density 0.037%

    No Known Activations