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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    serviceName
    -0.07
     Give
    -0.07
     �
    -0.06
    ['_
    -0.06
     好
    -0.06
    ΑΘ
    -0.06
    .Base
    -0.06
     Я
    -0.06
    Sim
    -0.06
     laten
    -0.06
    POSITIVE LOGITS
     golden
    0.08
    .pick
    0.07
     gren
    0.06
    .segment
    0.06
     encourages
    0.06
     duct
    0.06
    ",$
    0.06
    fastcall
    0.06
     pain
    0.06
     qemu
    0.06
    Act Density 0.044%

    No Known Activations