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

    Neuronpedia

    INDEX
    Explanations

    delivery drivers and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     \
    0.77
     enggak
    0.67
     as
    0.66
     étend
    0.64
     aplatis
    0.63
     jeweler
    0.62
     Și
    0.60
     grueling
    0.60
    രള
    0.60
     stucco
    0.59
    POSITIVE LOGITS
    in
    1.00
    at
    0.98
    v
    0.96
    service
    0.89
    delivery
    0.88
    h
    0.87
    b
    0.82
    w
    0.81
    some
    0.80
    ant
    0.75
    Act Density 0.004%

    No Known Activations