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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    《
    0.48
     Roblox
    0.39
     《
    0.37
    characters
    0.36
    лекет
    0.36
    Collide
    0.36
     Fortnite
    0.35
     Canning
    0.35
    HNO
    0.35
    Requested
    0.34
    POSITIVE LOGITS
     Pulp
    0.66
    Paras
    0.54
    Shaw
    0.52
     pulp
    0.51
     Shaw
    0.51
    Rear
    0.50
     Casablanca
    0.50
     shaw
    0.48
    Brazil
    0.48
    casino
    0.48
    Act Density 0.007%

    No Known Activations