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

    Neuronpedia

    INDEX
    Explanations

    payment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     psz
    -0.07
    |{↵
    -0.06
    Wnd
    -0.06
    男子
    -0.06
     адміністратив
    -0.06
    -F
    -0.06
    Climate
    -0.06
    POSITE
    -0.06
    igg
    -0.06
     dispatch
    -0.06
    POSITIVE LOGITS
    jan
    0.07
     происходит
    0.06
    INV
    0.06
    нике
    0.06
    ynch
    0.06
     держави
    0.06
     cố
    0.06
     сель
    0.06
     revolves
    0.06
     texte
    0.06
    Act Density 0.068%

    No Known Activations