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

    Neuronpedia

    INDEX
    Explanations

    media formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assistants
    -0.07
    .prot
    -0.07
     Recommended
    -0.07
     brushes
    -0.07
     wich
    -0.07
     Ambient
    -0.06
     awareness
    -0.06
     элем
    -0.06
     simult
    -0.06
     wr
    -0.06
    POSITIVE LOGITS
    алось
    0.07
    ались
    0.06
    .Atoi
    0.06
    -Headers
    0.06
    WhiteSpace
    0.06
    Nach
    0.06
     bagi
    0.06
    ματος
    0.06
    (GPIO
    0.06
    ับท
    0.06
    Act Density 0.059%

    No Known Activations