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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on obligation statements phrased in the passive voice—especially the “need to be taken” construction.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     policeman
    -0.07
    foundland
    -0.07
     alc
    -0.07
     Lebanon
    -0.06
    Parking
    -0.06
     domest
    -0.06
     commute
    -0.06
     choices
    -0.06
    .djang
    -0.06
     Baz
    -0.06
    POSITIVE LOGITS
     renamed
    0.07
    ]
↵
↵
    0.07
    ===============
    0.06
    ―
    0.06
    ↵
↵
↵
    0.06
    ]
↵
    0.06
    ọ
    0.06
    oky
    0.06
     особливо
    0.06
    �
    0.06
    Act Density 0.031%

    No Known Activations