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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ern
    -0.10
    nection
    -0.07
     ro
    -0.07
    .getLeft
    -0.07
    aty
    -0.06
    .G
    -0.06
    rado
    -0.06
    έντ
    -0.06
     Nice
    -0.06
     summon
    -0.06
    POSITIVE LOGITS
    (Job
    0.06
     obě
    0.06
     workplaces
    0.06
    �
    0.06
     nebezpeč
    0.06
    >'
↵
    0.06
    .DataAccess
    0.06
     Nina
    0.05
     블
    0.05
     Bill
    0.05
    Act Density 0.000%

    No Known Activations