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

    Neuronpedia

    INDEX
    Explanations

    contract hiring

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Professor
    0.46
    Professor
    0.44
     Funktion
    0.42
    zero
    0.42
    position
    0.40
    professor
    0.40
     Position
    0.38
    ben
    0.38
    remember
    0.38
     POSITION
    0.38
    POSITIVE LOGITS
     contracting
    0.56
     contractor
    0.47
     virtual
    0.46
     contract
    0.41
     contraction
    0.40
     Contracting
    0.40
     req
    0.38
     having
    0.38
     permanent
    0.38
    虚拟
    0.38
    Act Density 0.003%

    No Known Activations