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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron detects verbs that signal career moves or job‐related transitions (e.g. joined, moved).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Jag
    -0.07
     muht
    -0.07
     вій
    -0.07
    ebra
    -0.06
     Guild
    -0.06
    he
    -0.06
     chút
    -0.06
     Falls
    -0.06
     Hughes
    -0.06
    POSITIVE LOGITS
    mentor
    0.07
    .i
    0.07
    ίνει
    0.06
     Pres
    0.06
    <quote
    0.06
     ให
    0.06
    Private
    0.06
     systematically
    0.06
     Views
    0.06
    uali
    0.06
    Act Density 0.024%

    No Known Activations