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

    Neuronpedia

    INDEX
    Explanations

    MPs

    np_max-act · gemini-2.0-flash

    This neuron detects tokens in category lines that denote parliamentary membership (e.g. “MPs,” “Members,” “for,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     dispozici
    -0.06
     Epid
    -0.06
     lent
    -0.06
     browse
    -0.06
    _TREE
    -0.06
    575
    -0.06
    Services
    -0.06
    Legend
    -0.06
    ose
    -0.06
     Folder
    -0.06
    POSITIVE LOGITS
    汽
    0.07
    _OP
    0.07
     inev
    0.07
     klein
    0.07
     đạt
    0.06
    ishes
    0.06
     الأح
    0.06
    -rise
    0.06
    币
    0.06
    罚
    0.06
    Act Density 0.004%

    No Known Activations