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

    Neuronpedia

    INDEX
    Explanations

    terms related to reception and office environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    office, receptionist, station, desk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    må
    -0.40
     something
    -0.35
     Roman
    -0.34
    SimpleName
    -0.33
     poverty
    -0.33
     Luke
    -0.32
    assertThat
    -0.32
     épu
    -0.31
     Penn
    -0.30
     šk
    -0.30
    POSITIVE LOGITS
     receptionist
    0.73
    liceerd
    0.63
    сылкі
    0.61
     Geſch
    0.59
    staff
    0.59
     endregion
    0.58
     ſehr
    0.58
     initComponents
    0.57
     concierge
    0.57
     beſch
    0.57
    Act Density 0.002%

    No Known Activations