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
    entries
    -0.07
     Ψ
    -0.06
    ACHINE
    -0.06
     ngũ
    -0.06
     macros
    -0.06
    uenta
    -0.06
    |x
    -0.06
    X
    -0.06
    коз
    -0.06
    _ctor
    -0.06
    POSITIVE LOGITS
    Workers
    0.07
    .sales
    0.07
     Wildlife
    0.07
     damer
    0.06
    igger
    0.06
    NavItem
    0.06
    pageNumber
    0.06
     {}↵↵
    0.06
     här
    0.06
     Exact
    0.06
    Act Density 0.055%

    No Known Activations