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

    Neuronpedia

    INDEX
    Explanations

    dental

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Texto
    -0.07
     safer
    -0.07
     welche
    -0.07
    IRR
    -0.07
    Blog
    -0.06
     immediate
    -0.06
     Fever
    -0.06
    ObjectOfType
    -0.06
    Usuarios
    -0.06
     Smart
    -0.06
    POSITIVE LOGITS
     معنی
    0.07
    package
    0.06
    mland
    0.06
    ulled
    0.06
    -
    0.06
    tparam
    0.06
    attachment
    0.06
     trespass
    0.06
    _cap
    0.06
    ンプ
    0.06
    Act Density 0.006%

    No Known Activations