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

    Neuronpedia

    INDEX
    Explanations

    technical and security contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crowns
    0.53
     General
    0.50
    General
    0.48
    Feder
    0.47
    Custom
    0.47
    Selected
    0.46
    crown
    0.46
    Wilson
    0.46
    PC
    0.45
    Crown
    0.45
    POSITIVE LOGITS
     unsc
    0.48
     unsolved
    0.47
     enquire
    0.46
     monotonically
    0.45
     empieza
    0.45
     unsol
    0.45
     धारा
    0.44
     solvers
    0.44
     persevere
    0.44
    안
    0.44
    Act Density 0.000%

    No Known Activations