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

    Neuronpedia

    INDEX
    Explanations

    the start of HTML or PHP code blocks

    oai_token-act-pair · gemini-2.0-flash

    php, import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.75
    tvguidetime
    -0.72
     تضيفلها
    -0.72
     réguli
    -0.71
    EndContext
    -0.71
     تانيه
    -0.70
    endphp
    -0.68
     faſt
    -0.68
     preſent
    -0.68
    PyExc
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.49
     L
    0.49
     $
    0.47
    ParallelGroup
    0.46
     mixed
    0.46
     
    0.45
     Han
    0.45
     (
    0.44
     r
    0.44
     string
    0.44
    Act Density 0.064%

    No Known Activations