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

    Neuronpedia

    INDEX
    Explanations

    Ability to do things

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the token “something.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     trường
    -0.06
    .:.
    -0.06
    $client
    -0.06
     IOError
    -0.06
    卢
    -0.06
    ']=="
    -0.06
    Expired
    -0.06
    strcasecmp
    -0.06
     cent
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    jo
    0.08
     neden
    0.07
     Teach
    0.07
    -Mobile
    0.07
        ↵↵
    0.06
     süre
    0.06
     moda
    0.06
    ixo
    0.06
     thuyết
    0.06
     adjustable
    0.06
    Act Density 0.001%

    No Known Activations