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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    mathematical expressions and their simplifications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    >"
    -0.06
    ...'
    -0.06
    +'
    -0.06
     thirteen
    -0.06
    (links
    -0.06
    ávající
    -0.05
    Enemy
    -0.05
    '?
    -0.05
    (conn
    -0.05
    итися
    -0.05
    POSITIVE LOGITS
    {|
    0.08
     withstand
    0.07
    luğ
    0.07
    ▍▍▍▍▍▍▍▍
    0.07
    ofs
    0.07
     �
    0.07
     Speak
    0.07
     Floor
    0.07
    �
    0.07
    рива
    0.07
    Act Density 0.004%

    No Known Activations