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

    Neuronpedia

    INDEX
    Explanations

    URLs and domain names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Untuk
    0.39
     YouTube
    0.38
    key
    0.37
     Clean
    0.37
     Online
    0.37
     Coral
    0.37
    Chan
    0.37
     Forst
    0.37
     Village
    0.36
     Chan
    0.36
    POSITIVE LOGITS
     valleys
    0.40
     recoveries
    0.40
     risulta
    0.40
    Dockerfile
    0.40
     impedances
    0.39
     vegg
    0.39
     amenity
    0.39
    RestorePolicy
    0.39
     قدیم
    0.38
     verschil
    0.38
    Act Density 0.000%

    No Known Activations