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

    Neuronpedia

    INDEX
    Explanations

    discussing arguments and logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    사지
    -0.07
    Bean
    -0.06
     UIStoryboard
    -0.06
    directive
    -0.06
    itude
    -0.06
    -progress
    -0.06
    .free
    -0.06
    �
    -0.06
    ""
    -0.06
     genellikle
    -0.06
    POSITIVE LOGITS
     symp
    0.06
    -flight
    0.06
    (man
    0.06
    (prompt
    0.06
    :add
    0.06
    [B
    0.06
     Hawkins
    0.06
    cerer
    0.06
     Trouble
    0.06
     imread
    0.05
    Act Density 0.003%

    No Known Activations