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

    Neuronpedia

    INDEX
    Explanations

    Mechanical components

    np_max-act · gemini-2.0-flash

    The neuron fires on individual technical part names or component labels (e.g. shroud, insert, member, ring, flange) in patent‐style mechanical descriptions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     déf
    -0.07
     Kaz
    -0.07
    eck
    -0.07
     takip
    -0.07
    职
    -0.07
     IS
    -0.07
     Ey
    -0.07
     uğ
    -0.06
     Teknik
    -0.06
     Quiz
    -0.06
    POSITIVE LOGITS
     înt
    0.06
    овані
    0.06
    ську
    0.06
     спис
    0.06
    _LEN
    0.06
    venes
    0.06
    .getUserId
    0.06
    uther
    0.06
    .ListView
    0.05
    ่าอ
    0.05
    Act Density 0.063%

    No Known Activations