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

    Neuronpedia

    INDEX
    Explanations

    Technical devices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foot
    -0.07
     scar
    -0.07
     destruction
    -0.07
     dissertation
    -0.07
    .way
    -0.07
     Volt
    -0.07
     live
    -0.07
    ICTURE
    -0.07
     merely
    -0.07
     keys
    -0.07
    POSITIVE LOGITS
    ]"↵
    0.06
    kv
    0.06
    Tên
    0.06
    яется
    0.06
     Farage
    0.06
    (program
    0.06
     작은
    0.05
     crist
    0.05
     Конститу
    0.05
     mente
    0.05
    Act Density 0.043%

    No Known Activations