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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing scoring events and game outcomes in sports reporting (for example “proved,” “score,” “victory,” “lead,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Shapes
    -0.06
     giải
    -0.06
    _thumbnail
    -0.06
    enet
    -0.06
     login
    -0.06
    _opt
    -0.06
     THREE
    -0.06
     missions
    -0.06
     blends
    -0.06
    opening
    -0.05
    POSITIVE LOGITS
    \P
    0.07
     buyer
    0.07
     Straight
    0.07
    :H
    0.07
    мами
    0.07
    (/^
    0.07
    _WAIT
    0.07
    >(*
    0.07
    >r
    0.07
     latino
    0.06
    Act Density 0.011%

    No Known Activations