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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    This neuron detects the “Show HN:” post header marker (i.e. the “HN:” in “Show HN:” headings).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _NOTIFY
    -0.07
     quieres
    -0.07
    hari
    -0.07
     kino
    -0.06
     Rat
    -0.06
     mysl
    -0.06
     على
    -0.06
    correct
    -0.06
     pas
    -0.06
    iteit
    -0.06
    POSITIVE LOGITS
    CodeAt
    0.07
    assi
    0.07
     hostel
    0.06
    GRESS
    0.06
    ！');↵
    0.06
    ！");↵
    0.06
    ональ
    0.06
    席
    0.06
    ’l
    0.06
     Brend
    0.06
    Act Density 0.000%

    No Known Activations