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

    Neuronpedia

    INDEX
    Explanations

    employees supervising

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pport
    1.02
    }.$
    1.01
    id
    1.00
    al
    0.98
    賴
    0.97
    アイス
    0.93
    as
    0.93
    ca
    0.93
    らす
    0.91
    KI
    0.91
    POSITIVE LOGITS
     onlookers
    0.99
     oversee
    0.96
     educate
    0.92
     conceal
    0.89
     supervise
    0.89
     RSP
    0.88
     همه
    0.86
     employees
    0.86
     devote
    0.85
     investigators
    0.85
    Act Density 0.217%

    No Known Activations