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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     exposed
    -0.07
     Shea
    -0.07
    ㅒ
    -0.07
    喤
    -0.07
    荖
    -0.07
    �
    -0.07
    俗
    -0.07
    .PLL
    -0.07
     LOD
    -0.07
    oola
    -0.06
    POSITIVE LOGITS
    _age
    0.08
    -independent
    0.08
    ClassName
    0.07
    Block
    0.07
    Company
    0.07
    בינ
    0.07
    paragraph
    0.07
    uty
    0.07
     antibodies
    0.07
    .dirname
    0.07
    Act Density 0.009%

    No Known Activations