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

    Neuronpedia

    INDEX
    Explanations

    referral, recommendation, networking, leads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ين
    0.57
     Está
    0.50
     }.
    0.48
     té
    0.47
     沒有
    0.46
     be
    0.46
     esté
    0.45
    ISING
    0.45
     residing
    0.44
    ITE
    0.44
    POSITIVE LOGITS
    av
    0.60
    ට්ට
    0.54
    correct
    0.53
     distributors
    0.53
    prism
    0.51
    wires
    0.50
    Restaurants
    0.50
    vertical
    0.49
    restrict
    0.49
     advertisers
    0.49
    Act Density 0.337%

    No Known Activations