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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ським
    -0.07
     sprawling
    -0.07
    .D
    -0.06
     Plato
    -0.06
     pizza
    -0.06
     Carson
    -0.06
     Concent
    -0.06
    Defense
    -0.06
     and
    -0.06
     LICENSE
    -0.06
    POSITIVE LOGITS
    Lab
    0.07
    get
    0.07
    Mat
    0.07
    (random
    0.06
    _mgmt
    0.06
     absurd
    0.06
     갤
    0.06
    (dic
    0.06
     scre
    0.06
    slider
    0.06
    Act Density 0.248%

    No Known Activations