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

    Neuronpedia

    INDEX
    Explanations

    animals eating

    np_max-act · gemini-2.0-flash

    The neuron activates on words and phrases describing predatory actions or hunting—e.g. capturing, ambushing, taking down prey.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ABS
    -0.07
    -stage
    -0.07
    .enc
    -0.07
    /Z
    -0.06
     Invoke
    -0.06
     Resets
    -0.06
    clus
    -0.06
     clue
    -0.06
    igar
    -0.06
    flatMap
    -0.06
    POSITIVE LOGITS
    mal
    0.07
     IMPLIED
    0.06
    ‌شوند
    0.06
    %);↵
    0.06
    (al
    0.06
     hesitant
    0.06
     Danielle
    0.06
    ạp
    0.06
    อให
    0.06
     shimmer
    0.06
    Act Density 0.024%

    No Known Activations