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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ️
    -0.07
     Thế
    -0.07
     laisse
    -0.07
    gzip
    -0.07
    (productId
    -0.07
    わせ
    -0.07
     Lans
    -0.07
     moons
    -0.06
    inx
    -0.06
    (Calendar
    -0.06
    POSITIVE LOGITS
    SCALL
    0.06
     mpi
    0.06
    _ib
    0.06
     courses
    0.06
     oath
    0.06
    stanov
    0.06
     errors
    0.06
     CIT
    0.06
    g
    0.06
     engine
    0.06
    Act Density 0.003%

    No Known Activations