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

    Neuronpedia

    INDEX
    Explanations

    .,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    企業
    -0.07
    skými
    -0.06
    .parameters
    -0.06
     libros
    -0.06
     forgetting
    -0.06
    işti
    -0.06
    _vlan
    -0.06
     GRE
    -0.06
    Sr
    -0.06
    helpers
    -0.06
    POSITIVE LOGITS
     penny
    0.07
     pj
    0.07
    thin
    0.06
     xin
    0.06
    toc
    0.06
    ("--
    0.06
     anonymous
    0.06
     Kamp
    0.06
     name
    0.06
     pleasantly
    0.06
    Act Density 0.005%

    No Known Activations