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

    Neuronpedia

    INDEX
    Explanations

    prepositions and articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cafe
    -0.06
     Administration
    -0.06
     Easily
    -0.06
    急
    -0.06
     Command
    -0.06
     command
    -0.06
    Usuarios
    -0.06
     servic
    -0.06
     iniciar
    -0.06
     místní
    -0.06
    POSITIVE LOGITS
    خص
    0.07
     arguably
    0.07
     Bd
    0.07
    iten
    0.06
    ỳ
    0.06
    leader
    0.06
    orst
    0.06
    clid
    0.06
    _tunnel
    0.06
    озна
    0.06
    Act Density 0.045%

    No Known Activations