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

    Neuronpedia

    INDEX
    Explanations

    replace with code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    veis
    -0.07
    EmptyEntries
    -0.07
     области
    -0.06
    Bits
    -0.06
     Tips
    -0.06
    remainder
    -0.06
     pořad
    -0.06
    veys
    -0.06
    全球
    -0.06
     mi
    -0.06
    POSITIVE LOGITS
    :value
    0.06
     �
    0.06
    .'</
    0.06
    }'↵
    0.06
     смерти
    0.06
    ypy
    0.06
    ete
    0.06
     cherche
    0.06
     profession
    0.06
     initial
    0.06
    Act Density 0.019%

    No Known Activations