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

    Neuronpedia

    INDEX
    Explanations

    Online forms/reservations/claims

    np_max-act · gemini-2.0-flash

    The neuron fires on standalone section‐header words or labels (e.g. “Bookings,” “Payment,” “Shipping,” “Returns,” “Entries,” “Updates,” etc.) that introduce new sections.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     prohibit
    -0.07
    ैठ
    -0.07
     trout
    -0.06
    %),
    -0.06
    track
    -0.06
    dirty
    -0.06
     Whit
    -0.06
    dbus
    -0.06
    ]).
    -0.06
    Thông
    -0.06
    POSITIVE LOGITS
     origen
    0.07
    christ
    0.07
    .cbo
    0.06
     blowing
    0.06
     �
    0.06
       ↵    ↵
    0.06
    .Dialog
    0.06
    .Double
    0.06
    reglo
    0.06
     �
    0.06
    Act Density 0.069%

    No Known Activations