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

    Neuronpedia

    INDEX
    Explanations

    non-English characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اتاق
    -0.07
     straightforward
    -0.06
    fee
    -0.06
     INIT
    -0.06
    registro
    -0.06
     Sacred
    -0.06
     anatom
    -0.06
    .toolbar
    -0.06
     Ledger
    -0.06
     tac
    -0.06
    POSITIVE LOGITS
    �
    0.07
     wes
    0.06
    ails
    0.06
    ΩΣ
    0.06
    osex
    0.06
    олож
    0.06
     dit
    0.06
    .Rem
    0.06
     purchasers
    0.06
     زیاد
    0.06
    Act Density 0.020%

    No Known Activations