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

    Neuronpedia

    INDEX
    Explanations

    dust and settlement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ग्वि
    0.47
    makarna
    0.47
    arschijnlijk
    0.43
    শিকান্ত
    0.42
     incomple
    0.41
    ()=>{
    0.41
    Olá
    0.41
    kron
    0.41
     prevented
    0.40
    Kel
    0.40
    POSITIVE LOGITS
     statistical
    0.47
     -
    0.46
    的总
    0.46
     collaboration
    0.46
     Schools
    0.45
     swarm
    0.45
    CIP
    0.44
     gym
    0.43
     Courthouse
    0.43
     சமூக
    0.43
    Act Density 0.002%

    No Known Activations