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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gratis
    -0.07
    طه
    -0.07
    .Vertical
    -0.07
     includ
    -0.07
    meyi
    -0.06
    .Gr
    -0.06
     iVar
    -0.06
     kah
    -0.06
     circumference
    -0.06
    เมตร
    -0.06
    POSITIVE LOGITS
     Leaders
    0.07
     EMC
    0.07
     Medal
    0.06
     SDL
    0.06
    _System
    0.06
     kend
    0.06
     próximo
    0.06
     McCl
    0.06
    áři
    0.06
     Few
    0.06
    Act Density 0.052%

    No Known Activations