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

    Neuronpedia

    INDEX
    Explanations

    say "IT/network" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rement
    -0.07
     Hopkins
    -0.07
    角色
    -0.07
     unfold
    -0.07
    eur
    -0.07
     compartment
    -0.06
     окон
    -0.06
    _O
    -0.06
    _channels
    -0.06
     Strength
    -0.06
    POSITIVE LOGITS
     give
    0.06
    valuator
    0.06
     gives
    0.06
     stringWith
    0.06
    .viewModel
    0.06
    -Col
    0.06
    วไป
    0.06
    ุญาต
    0.06
    oulouse
    0.06
     WiFi
    0.06
    Act Density 0.043%

    No Known Activations