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

    Neuronpedia

    INDEX
    Explanations

    technical parameters and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     নেই
    0.45
     அடுத்து
    0.45
     Alexander
    0.44
    assignmentItems
    0.42
     බල
    0.41
    escence
    0.40
     الفلسطيني
    0.40
     안
    0.40
    landi
    0.40
    花园
    0.40
    POSITIVE LOGITS
     positives
    0.46
     protagon
    0.44
    हमने
    0.44
     edible
    0.43
     authorizations
    0.43
    eds
    0.43
     gedacht
    0.43
     deliverables
    0.43
    łach
    0.42
     intelekt
    0.42
    Act Density 0.001%

    No Known Activations